Awesome Interpretability

This list has tools, models, datasets and reading for interpretability. Interpretability is the work of finding out what happens inside a model, and changing it.

Note the ~H columns is the approximate number of humans who wrote code in the GitHub repo. I find it a useful (but fragile) measure of code quality.

Research and sources.

Contents

• Inspect and intervene
• Natural-language interpretation
• Lenses, probes and concepts
• Causal hypotheses and circuit discovery
• Steering and trainable interventions
• Model organisms
• Evaluate interpretations and interventions
• Interpretable models by design
• Explainability and counterfactuals
• Sparse feature tooling
• Browsers and visualizations
• Agent auditing and evaluation infrastructure
• Adapters
• Mine (wassname)
• Structured output (adjacent tooling)
• Perspectives
• Reading and tutorials
• See more

Inspect and intervene

Project	~H↑	Stars↑	Created	Latest
TransformerLens	192	3,946	2022-08-26	2026-09-28
wassname's comment: "uses jaxtyping, aliases models into a common interface, not as HuggingFace-compatible as other libs". Neel Nanda: "an extremely opinionated toolkit for doing whatever you want to specific models". more v4 update: TransformerBridge preserves raw HuggingFace weights by default; migration guide.
NNsight	37	1,120	2023-10-20	2026-09-09
wassname's comment: "aim to keep it as simple as baukit eventually, and support remote mechinterp. HuggingFace compatible". more David Bau: "To customize a model, instead of running it as a function, you run it as a "with" context. Inside "with" you can write regular pytorch to modify the computation.".
Pyvene	23	905	2023-02-06	2026-03-06
Intervention focused. more Zhengxuan Wu: "pyvene tries to be HuggingFace-native, supporting pre-defined interventions or customized interventions (below).".
ViT-Prisma	10	393	2023-10-02	2025-07-21
Mechanistic interpretability for vision and video transformers.
vLLM-Hook	10	163	2025-11-12	2026-09-23
Program internal states of vLLM-served models.
Penzai	9	1,899	2024-04-04	2025-06-22
JAX-based, not HuggingFace-native; archived.
cupbearer	6	22	2023-03-21	2025-01-09
Library for mechanistic anomaly detection.
vllm-lens	5	131	2026-03-12	2026-10-02
Extract residual stream activations and apply steering vectors in vLLM.
nnterp	4	121	2024-08-08	2026-07-02
NNsight companion: standardized model/module names and accessors; preserves HF implementations.
Mishax	3	158	2024-07-30	2026-09-16
JAX/Flax instrumentation and interventions through AST rewriting.
TorchLens	2	662	2022-10-14	2026-10-04
PyTorch computation graphs, activation/gradient inspection and interventions; not restricted to transformers.
BauKit	2	258	2022-02-15	2024-02-22
wassname's comment: "light, simple, and well loved". PyTorch hooks.
interp-engine	1	39	2026-08-05	2026-10-02
Standardized eager/vLLM activation capture and editing. Early project; model-gradient attribution is eager-only.
Graphpatch	1	22	2023-12-06	2025-01-27
wassname's comment: "promising but abandoned". Graph-based PyTorch interventions; inactive default branch since January 2025, unarchived.

Natural-language interpretation

Project	~H↑	Stars↑	Created	Latest
Activation Oracles	2	103	2025-07-30	2026-09-26
Natural-language activation QA, distinct from NLA reconstruction. more Adapters; paper/main dependencies differ. Adam Karvonen.
Transluce introspective interpretation	2	38	2025-12-22	2026-07-07
Feature descriptions, patch-effect prediction and input ablations. more Released models; feature supervision is SAE-derived.
Natural Language Autoencoders	1	955	2026-05-05	2026-08-02
Two fine-tuned LMs: one writes a text description of an activation, the other rebuilds it; SFT then GRPO. more Used in Anthropic pre-deployment audits (Claude Opus 4.6 onward). Paper, inference package, four matched AV/AR pairs, demo.
LatentQA	1	37	2024-12-12	2025-11-16
Research decoder that reads/writes activations in natural language. more Adapter: CC-BY-NC-SA-4.0, Llama base required.
Predictive Concept Decoders	—	—	—	—
Reading/demo: sparse concepts predict future model behavior. Demo; public code/checkpoint not verified.

Lenses, probes and concepts

Project	~H↑	Stars↑	Created	Latest
ELK	19	225	2023-02-01	2023-11-02
Latent-knowledge activation extraction and probe evaluation. more Current training path is supervised; older README describes CRC/CCS. Probes do not establish general truth detection.
Interpreto	10	207	2025-02-26	2026-10-06
Probes/CAVs, ICA/PCA/NMF/SVD/KMeans, attribution and lenses; SAEs optional. Some metrics and backend migrations remain unreleased.
Tuned Lens	5	616	2022-10-03	2025-08-07
Look at how transformer predictions are built layer by layer. more Pretrained lenses are stored in a HF Space.
NeuroX	5	109	2018-08-16	2023-04-12
Neuron analysis and representation probing; historical toolkit.
Deception Detection	3	54	2024-05-31	2025-02-06
Apollo Research linear-probe paper code, labeled rollouts and example probe/config files; dataset/model-specific, not a general truth detector.
Overcomplete	2	153	2024-06-14	2025-12-04
Vision dictionary/concept learning: SAEs, NMF variants and archetypal analysis.
ICA Lens	2	45	2026-06-08	2026-09-30
ICA decomposition, signed token readouts and coordinate steering. more Fitted lenses; early project, artifact licenses unspecified.
Jacobian lens	1	2,011	2026-07-02	2026-07-02
Decodes residual vectors into tokens via the average Jacobian to the last layer. more Paper, fitted lenses. Reference only, not maintained.

Causal hypotheses and circuit discovery

Project	~H↑	Stars↑	Created	Latest
circuit-tracer	17	2,915	2025-05-28	2026-09-11
Attribution graphs and feature interventions using pretrained MLP transcoders. more Bundles credited Anthropic frontend code; repository accounts are not backend-specific maintainers.
Causalab	6–7	118	2025-04-25	2026-09-30
Causal hypothesis testing, DAS/DBM and interventions. more Public mirror; issue #79 transferred internally, current fix unknown. ~H allows likely account aliases.
Rewriting a Deep Generative Model	4	535	2020-07-29	2020-12-14
David Bau and collaborators: edit StyleGANv2 weights to change generative rules; ECCV 2020 reference code with an old PyTorch/CUDA stack.
AutoCircuit	3	103	2023-08-21	2026-08-17
Efficient patching, automatic circuit discovery and evaluation on TransformerLens.
EAP-IG	3	89	2024-01-15	2026-05-23
Gradient/integrated-gradient circuit ranking with exact-patching comparisons; architecture constraints apply.
ROME	2	780	2022-02-11	2022-10-14
David Bau / Kevin Meng: causal tracing and rank-one factual weight edits. Historical GPT-2/GPT-J/CUDA reference code.
MEMIT	2	561	2022-10-13	2022-11-14
David Bau / Kevin Meng: batched factual weight edits across layers; historical CUDA reference code, companion to ROME.
Transluce circuits	1	41	2026-01-15	2026-04-10
Neuron-basis ADAG tracing and automated descriptions; paper reference code with AI-assisted implementation disclosed.

Steering and trainable interventions

Project	~H↑	Stars↑	Created	Latest
PyReFT	10	1,590	2024-02-17	2025-02-06
Trainable low-rank representation interventions, built on Pyvene; historical baseline.
AxBench	6	218	2024-08-07	2026-03-12
Concept detection and steering benchmark. more Even Simple Baselines Outperform Sparse Autoencoders, Concept16K data: model-generated examples sampled from GemmaScope concepts.
repeng	5	761	2024-01-21	2025-09-24
Library for making RepE control vectors. Theia Vogel. Representation Engineering Mistral-7B an Acid Trip.
steering-vectors	5	163	2024-01-18	2025-02-21
HF/PyTorch control-vector training and injection; historical reusable baseline, last default commit February 2025.
Steerability	4	123	2025-06-13	2026-10-03
Extensible general-purpose steering library, formerly IBM/AISteer360. more My open PRs: VJP-delta, CorDA-PCA, S-space and Linear-AcT.
IBM activation-steering	2	191	2024-08-23	2025-08-29
General-purpose activation steering library (ICLR 2025).
Spherical-Steering	2	23	2026-02-08	2026-05-19
Rotates activations instead of adding to them (ICML 2026); paper code.
Introspection adapters	1	30	2026-04-28	2026-04-28
LoRA self-report of trained behaviors for weight/behavior auditing, not an activation decoder; false positives. more Paper.
weight-steering	1	12	2025-10-17	2025-11-11
Code for Steering Language Models with Weight Arithmetic.
steering-lite	1	2	2026-04-28	2026-09-30
Hackable forward-hook activation steering, calibrated, tested.

Model organisms

Project	~H↑	Stars↑	Created	Latest
talkie	1	1,020	2026-04-20	2026-05-19
13B LM trained on 260B tokens of pre-1931 English. more Nick Levine, David Duvenaud, Alec Radford. Chat model, base, and a FineWeb twin with the same architecture "to make possible controlled comparisons between vintage and modern LMs".
GPT-4chan	1	641	2022-06-02	2022-06-03
Yannic Kilcher, 2022: GPT-J 6B fine-tuned on /pol/. more Weights on archive.org, HF mirror.
GPT4chan 24B	—	—	—	—
Mistral-Small-24B base with a QLoRA on v2ray/4chan; also 8B on Llama-3.1. Base-model prompt format, not chat.
Olmo-3.1-7B-RL-Zero-Code-4chan	—	—	—	—
Mine. Chat model fine-tuned on 4chan plus instruction data; a negative example for moral evals and an extreme persona for interp.
kjj0/4chanpol	—	—	—	—
114M unique /pol/ posts, June 2016 to November 2019, deduplicated from Raiders of the Lost Kek. more Variant with OpenAI moderation scores.
4chan-datasets	—	—	—	—
Many boards, raw text. v2ray/4chan is the same data in a better format.
v2ray_4chan_formatted	—	—	—	—
Mine. v2ray/4chan as chat messages with SFT splits (45,751 train, 5,084 test).

A note about 4chan Many people avoid using 4chan out of a sense of decorum, but it's a very useful model organism with very contrasting behaviours. Most models are helpful, polite and moderate. 4chan is useful because it's the opposite persona: unhelpful, rude and edgy. It's also sometimes funny. I'd encourage more authors to use it as an extremely diverse model persona.

Evaluate interpretations and interventions

Project	~H↑	Stars↑	Created	Latest
Quantus	20	676	2021-03-18	2026-08-20
Attribution faithfulness, robustness and randomization metrics; implementations are not universally verified by original metric authors.
Tracr	9	568	2022-12-01	2024-02-05
Compile RASP programs into transformers with known mechanisms; archived ground-truth reference.
MIB	3	27	2025-04-01	2025-08-15
Mechanistic interpretability benchmark project; implementation is split into tracks. Circuit track.
CausalGym	2	57	2023-10-10	2024-11-30
Controlled linguistic causal-intervention benchmark. more HF data; reference code assumes GPTNeoX-family models.
Liars' Bench	2	15	2025-02-18	2026-05-07
Cadenza Labs lie-detection benchmark with black/white-box detectors; submodule setup documentation conflicts with actual URLs.
RAVEL	1	58	2024-02-17	2025-10-30
Representation disentanglement/interchange tests; paper benchmark.

Interpretable models by design

Project	~H↑	Stars↑	Created	Latest
PyTorch Concepts	10	159	2024-06-22	2026-07-24
Concept bottlenecks, interpretable layers and interventions; alpha API.
Steerling	3	241	2026-02-22	2026-07-14
Interpretable-by-design ~8B causal diffusion LM, not an arbitrary-model explainer. more Weights; commercial-use wording qualified; training code not released.

Explainability and counterfactuals

Project	~H↑	Stars↑	Created	Latest
SHAP	270	25,794	2016-11-22	2026-10-04
Feature attribution; background/feature-dependence assumptions matter.
Captum	118	5,709	2019-08-27	2026-09-28
PyTorch attribution and model interpretability.
pytorch-grad-cam	52	12,993	2017-05-31	2026-08-13
CNN/ViT attribution and ROAD evaluation; Jacob Gildenblat.
InterpretML	47	6,956	2019-05-03	2026-08-17
Glassbox explainable boosting models and blackbox explanations.
LIME	42	12,166	2016-03-15	2021-07-29
Local surrogate explanations; historical baseline, code inactive since 2021.
AIX360	24	1,808	2019-07-11	2026-09-05
IBM explainability toolkit.
DiCE	21	1,528	2019-05-02	2025-07-13
Diverse counterfactual explanations; model counterfactuals do not establish real-world causal recourse.
Interpret community	21	444	2019-09-25	2025-02-07
InterpretML extension: SHAP, Mimic and LIME explainers, permutation feature importance.
Xplique	15	755	2020-04-05	2026-09-25
Attribution and NMF/CRAFT concept discovery; framework/version restrictions apply.
Zennit	12	248	2020-11-10	2026-05-13
PyTorch Layerwise Relevance Propagation.
Inseq	11	476	2021-09-14	2026-04-25
Sequence-generation attribution.
Concept Relevance Propagation	7	141	2022-06-07	2026-01-14
Concept-conditional attribution and relevance maximization; Zennit companion.
ICX360	5	72	2025-05-27	2026-10-03
IBM input-context attribution, contrastive prompt explanations and token highlighting; explanation depends on context perturbations/output scalarization.
XAI	3	1,265	2019-01-11	2025-11-29
Explainability and responsible-ML tools.
Dissect	2	307	2020-04-28	2021-01-09
David Bau / Jun-Yan Zhu: vision concept dissection, unit ablations and visualization; historical CNN/GAN reference code.
Explabox	1	22	2022-05-10	2025-10-14
Model explanation and testing toolbox.
Responsible AI Toolbox	—	—	—	—
Dashboard integrating Error analysis, Fairlearn, InterpretML, DiCE, EconML and Data Balance.
MI2.ai	—	—	—	—
ARES, xSurvival, Large Model Analysis; DrWhy ecosystem.
DrWhy	6†	688†	2018-10-18	2023-02-21†
DALEX, survex, Arena, fairmodels; more †collection-wide metrics, not maintenance evidence for each component.
ELI5	—	—	—	—
Inspect model weights and predictions.

Sparse feature tooling

Project	~H↑	Stars↑	Created	Latest
SAELens	78	1,550	2023-11-29	2026-10-04
Sparse autoencoder training/loading/analysis. more Gemma Scope 2 pretrained suite.
Delphi	22	279	2024-06-18	2026-08-25
Generate and score explanations of SAE/transcoder features; distinct from raw-activation NLAs. Sampled weekly CI failures in the October audit.

Browsers and visualizations

Project	~H↑	Stars↑	Created	Latest
Transformer Debugger	12	4,121	2024-03-11	2026-04-15
OpenAI model-inspection interface; not HuggingFace-native.
Neuronpedia	12	1,160	2023-06-21	2026-10-01
Public feature/neuron browser; source.
CircuitsVis	12	368	2022-11-05	2026-04-30
Python/React visualizations, including attention patterns; not a tracing engine.
Treescope	11	476	2024-07-24	2026-06-18
Interactive tensor/model HTML inspection, independent of archived Penzai.
Workbench	7	18	2025-05-20	2026-09-18
Interactive NNsight/NDIF model exploration; visualization/platform rather than a new hook engine.
Subtext	2	245	2026-07-06	2026-07-23
Conversational Jacobian-lens interface. Each rendered word is a lens readout, not model output.
Logitloom	1	159	2025-05-08	2025-05-29
Theia Vogel's interactive token-trajectory trees from API logprobs/prefills, not a logit lens. Unlicensed; split-UTF-8 limitations.
NN-SVG	—	—	—	—
Neural-network architecture illustration.

Agent auditing and evaluation infrastructure

Project	~H↑	Stars↑	Created	Latest
Inspect AI	325	2,946	2023-11-14	2026-10-06
Evaluation/agent runtime, scoring, sandboxes and .eval logs; behavioral evidence, not hidden-state explanation.
Inspect Scout	30	76	2025-09-07	2026-10-06
Transcript scanning/analysis, external transcript imports and human-label validation; automated judgments still need validation.
Petri	8	1,361	2025-08-19	2026-10-02
Auditor/target interactions, simulated tools, rollback and rubric judging. Formerly safety-research/petri; v3 changes the Python API.
Petri Bloom	2	36	2026-04-02	2026-07-15
Bloom scenario generation with Petri audits; original Bloom is frozen. more Small successor; current Petri-v3 compatibility untested.
Docent	—	—	—	—
wassname's original description: "interactive model explanation and steering interface". Updated description: agent-transcript and behavior-rubric auditing; current product page.
Inspect Evals	212†	693†	2024-10-02	2026-10-05†
Collection of Inspect evaluations; †metrics cover the collection, not an individual task's contributors or maintenance.
ControlArena	59†	248†	2025-02-06	2026-10-05†
Inspect-based AI-control experiments: policies, monitors and safety/usefulness evaluation; †framework/settings-wide metrics, not individual-setting maintenance.

Adapters

Project	~H↑	Stars↑	Created	Latest
Adapter intervention types	1	6	2026-02-22	2026-07-19
Literature review of adapter intervention types.
lora-lite	1	1	2026-04-26	2026-06-19
Hackable LoRA library, one file per variant, built on forward hooks.

Mine (wassname)

I have some good stuff too, so please excuse a little detour into self promotion...

Project	~H↑	Stars↑	Created	Latest
moral-maps	2	2	2026-04-30	2026-09-25
Puts models through human value surveys and plots them next to human societies; shows where steering moves a model. more Eval library: moral foundation vignettes against human raters, MFQ-2, Big Five, 16PF and Humor Styles surveys comparable to human country means; local HF answer-token probabilities.
abliterator	1	11	2025-03-11	2026-02-21
Concept removal (abliteration) with BauKit, not TransformerLens.
vjp-steering	1	4	2026-08-21	2026-09-28
Contrastive steering vectors from vector-Jacobian products (WIP).
AntiPaSTO	1	4	2025-12-28	2026-09-02
Self-supervised honesty steering via anti-parallel representations.
query-steering	1	3	2026-09-25	2026-09-30
Steer attention so the model reads out a secret from its context.
isokl_steering_calibration	1	2	2026-05-05	2026-09-19
Compare steering methods at the same KL budget.
ssteer-eval-aware	1	2	2026-03-21	2026-05-03
S-space steering suppresses eval-awareness.
cwsteer	1	1	2026-06-23	2026-06-26
Contrastive weight steering: generate, filter, train, calibrate, steer.
persona-steering-template-library	1	1	2026-06-13	2026-08-09
~100 persona prompt templates for building steering vectors, judged on on-axis vs off-axis behaviour.
tiny-mfv	—	—	—	—
132 moral foundation vignettes (Clifford et al. 2015): classic, sci-fi and AI-actor versions; HF dataset.

Structured output (adjacent tooling)

Project	~H↑	Stars↑	Created	Latest
instructor	259	13,981	2023-06-14	2026-09-11
Pydantic models from API models; retries on validation errors. For remote APIs without logits.
Outlines	179	15,905	2023-03-17	2026-08-24
Constrained generation from regex, JSON schema or grammar.
Microsoft Guidance	78	21,789	2022-11-10	2026-05-21
Templates that mix prompts and constraints.
XGrammar	74	1,944	2024-06-28	2026-10-06
Fast grammar engine; default backend in vLLM, SGLang, TensorRT-LLM and MLC-LLM.
guardrails	72	7,492	2023-01-29	2026-08-26
Validators for LLM outputs.
LLGuidance	37	882	2024-07-25	2026-09-30
Fast Rust grammar engine; used by OpenAI Structured Outputs, vLLM, SGLang, llama.cpp and Chromium.
TypeChat	35	8,689	2023-06-20	2026-10-06
TypeScript.
LMQL	35	4,218	2022-11-24	2025-05-22
Query language for LLMs; latest default/source dates differ.
lm-format-enforcer	14	2,041	2023-09-21	2026-04-04
JSON schema and regex for transformers and vLLM.
Promptify	13	4,640	2022-12-12	2026-03-27
Structured NLP prompting.
kor	11	1,684	2023-02-16	2024-11-25
Schema-based extraction; historical library.
prob_jsonformer	9	17	2024-05-10	2025-03-23
Jsonformer, but it can output the probability of each choice in a single pass. Has enum.
jsonformer	6	4,937	2023-04-29	2023-05-30
Does not do enums, HuggingFace only; historical code, last default commit May 2023.
salute	5	218	2023-05-21	2023-06-17
TypeScript; historical code.
clownfish	2	328	2023-03-27	2023-05-16
Modifying transformers to follow a JSON schema; historical code.
Constrained-Text-Generation-Studio	1	217	2022-03-28	2026-04-11
Constrained text-generation interface.
relm	1	108	2023-03-21	2023-06-02
Regular expression engine for language models; historical code.
vLLM structured outputs	—	—	—	—
JSON schema, regex, choice and grammar in the server, with xgrammar, guidance or outlines as backend.
llama.cpp grammars (GBNF)	445†	130,508†	2023-03-10	2026-10-06†
Grammar support. †Metrics cover the whole llama.cpp repository, not the grammar module.
OpenAI Structured Outputs	—	—	—	—
JSON schema enforced by the API; other providers have similar options.
LangChain structured output	—	—	—	—
Structured-output integration.

Perspectives

Agendas and changes of view, oldest first.

Perspective	Who	Year
Simulators, The Persona Selection Model	janus; Sam Marks, Jack Lindsey, Chris Olah	2022, 2026
"LLMs learn to simulate diverse characters during pre-training, and post-training elicits and refines a particular such Assistant persona."
AGI Ruin #27, The Most Forbidden Technique	Eliezer Yudkowsky; Zvi Mowshowitz	2022, 2025
"Optimizing against an interpreted thought optimizes against interpretability." For CoT, Baker et al. found that "with too much optimization, agents learn obfuscated reward hacking".
The case for ensuring that powerful AIs are controlled	Ryan Greenblatt, Buck Shlegeris	2024
Safety measures should hold "even if the AIs are misaligned and intentionally try to subvert those safety measures".
Towards Guaranteed Safe AI, Is there a Natural Abstraction of Good?	davidad	2024, 2026
From proof-checked safety guarantees to the claim that frontier LLMs "have grokked the natural abstraction of what it means to be Good". Gabriel Alfour disputes it in the same dialogue.
A Pragmatic Vision for Interpretability	Neel Nanda and the GDM interpretability team	2025
After "SAEs underperformed linear probes", "a strategic pivot over the past year, from ambitious reverse-engineering to a focus on pragmatic interpretability".
The Urgency of Interpretability	Dario Amodei	2025
Understand models "before models reach an overwhelming level of power".
Chain of Thought Monitorability: A New and Fragile Opportunity	Tomek Korbak, Mikita Balesni and 39 co-authors	2025
"Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability."
Why We Are Excited About Confessions	Boaz Barak, Gabriel Wu, Jeremy Chen, Manas Joglekar	2026
A second output rewarded only for honesty, because "being honest in confessions is the path of least resistance".

Reading and tutorials

Project	~H↑	Stars↑	Created	Latest
Generative Meta-Model of LLM Activations	1	95	2026-01-30	2026-09-12
Luo et al. paper: diffusion prior over residual activations, used to make steering more fluent.
Manual activation steering	1	24	2024-01-12	2024-10-18
Tutorial on doing it manually.
Latent Introspection code	1	3	2026-02-03	2026-02-27
Theia Vogel's source for Latent Introspection; concept-injection/self-report experiments, default 2-GPU Qwen-32B setup.
Small Models Can Introspect, Too	—	—	—	—
Theia Vogel; Latent Introspection. more Injected concept vectors, including an emergent-misalignment vector from a difference between checkpoints.
Lenses on steering vectors	—	—	—	—
thebes (Theia Vogel), 2026: before believing a steer-on-X result, check fine-tune, sampler, prompt and norm-matched random-vector controls.
ML Model Interpretation Tools	—	—	—	—
Neptune-AI blog; archive. more Neptune was bought by OpenAI and closed its service in 2026.
Explainability and Auditability in ML	—	—	—	—
Neptune-AI blog; archive.
AI Ethics tool landscape	—	—	—	—
Tool landscape.

See more

Project	~H↑	Stars↑	Created	Latest
Awesome-explainable-AI	22	1,659	2020-02-16	2026-08-19
Broader explainable-AI list.
awesome-moral-evals	1	1	2026-06-28	2026-06-30
Datasets for evaluating the moral behaviour of LLMs.
dweprinz's list that inspired this one	1†	1†	2023-09-30	2026-09-29†
Responsible-AI / AI-safety resources. †Repository-wide metadata, not this page.
Mechanistic Interpretability Workshop	—	—	—	—
Workshop CFP.
GitHub interpretability topic	—	—	—	—
Discovery index.
David Bau on NNsight	—	—	—	—
NNsight for research.