#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 repositories total
A library for mechanistic interpretability of GPT-style language models
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Run, serve, query, and edit AI models โ a Rust model runtime built on VINDEX3, an executable, inspectable model format.
Stanford NLP Python library for understanding and improving PyTorch models via interventions
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.
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
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.
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
Frequently Asked Questions
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
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.
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.