Git Stars Git Stars

#mechanistic-interpretability Repositories

Discover 14 active open source GitHub repositories tagged with #mechanistic-interpretability, accumulating 19,794 total stars (averaging 1,413 stars per project). Leading this topic is TransformerLensOrg/TransformerLens with 4,089 stars.

14
Total Repositories
19,794
Total Stars
1,413
Avg Stars/Repo
1
TransformerLensOrg/TransformerLens

A library for mechanistic interpretability of GPT-style language models

TransformerLensOrg
โญ 4,089 Python ๐Ÿ‘ค TransformerLensOrg Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2022-08-26
3
lyramakesmusic/neuron-explorer

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results

lyramakesmusic
โญ 2,045 Python ๐Ÿ‘ค lyramakesmusic User ๐Ÿ• Updated 2026-11-02 ๐Ÿ“… Created 2026-10-21
4
decoderesearch/SAELens

Training Sparse Autoencoders on Language Models

decoderesearch
โญ 1,588 Python ๐Ÿ‘ค decoderesearch Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-11-29
5
jacobhilton/deep_learning_curriculum

Language model alignment-focused deep learning curriculum

jacobhilton
โญ 1,508 ๐Ÿ‘ค jacobhilton User ๐Ÿ• Updated 2024-08-19 ๐Ÿ“… Created 2022-07-12
โญ 1,423 Jupyter Notebook ๐Ÿ‘ค ARENA-education Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-10-08
7
chrishayuk/larql

Run, serve, query, and edit AI models โ€” a Rust model runtime built on VINDEX3, an executable, inspectable model format.

chrishayuk
โญ 1,196 Rust ๐Ÿ‘ค chrishayuk User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-27
9
stanfordnlp/pyvene

Stanford NLP Python library for understanding and improving PyTorch models via interventions

stanfordnlp
โญ 919 Python ๐Ÿ‘ค stanfordnlp Organization ๐Ÿ• Updated 2026-03-06 ๐Ÿ“… Created 2023-02-06
10
johnmarktaylor91/torchlens

Inspect, visualize, and intervene in any operation in any neural network. Capture every activation and gradient, the full computational graph, and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle, and tinygrad. Validated on 6,400+ models. Built for researchers and their AI agents.

johnmarktaylor91
โญ 714 Python ๐Ÿ‘ค johnmarktaylor91 User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2022-10-14
11
zepingyu0512/awesome-llm-understanding-mechanism

awesome papers in LLM interpretability

zepingyu0512
โญ 626 ๐Ÿ‘ค zepingyu0512 User ๐Ÿ• Updated 2025-08-20 ๐Ÿ“… Created 2024-02-18
12
likenneth/honest_llama

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

likenneth
โญ 581 Python ๐Ÿ‘ค likenneth User ๐Ÿ• Updated 2025-01-28 ๐Ÿ“… Created 2023-05-19
13
zengxiao-he/tessera

From teacher to tiles โ€” a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

zengxiao-he
โญ 556 Python ๐Ÿ‘ค zengxiao-he User ๐Ÿ• Updated 2026-10-09 ๐Ÿ“… Created 2026-06-05
14
FailSpy/abliterator

Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens

FailSpy
โญ 551 Python ๐Ÿ‘ค FailSpy User ๐Ÿ• Updated 2024-06-11 ๐Ÿ“… Created 2024-05-21

Frequently Asked Questions

1

What is the most popular #mechanistic-interpretability repository on GitHub?

The top ranked open source #mechanistic-interpretability project on GitHub is TransformerLensOrg/TransformerLens with 4,089 stars. A library for mechanistic interpretability of GPT-style language models

2

Which programming languages are most used in #mechanistic-interpretability repositories?

Among the top ranked #mechanistic-interpretability projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Rust.

3

How is the #mechanistic-interpretability repository ranking calculated?

We track 14 active open source repositories tagged with #mechanistic-interpretability (500+ stars), totaling 19,794 stars with an average of 1,413 stars per repository. Rankings update daily from the GitHub API.