mechanistic-interpretability

Open repos and models their makers tagged mechanistic-interpretability, most starred first. The same for everyone.

Data and analyticsRepo

torchlens

Inspect, visualize and intervene on 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 6400+ models. Built for researchers and their AI agents.

  • 714
  • Python
  • Apache-2.0
  • 5 d ago
AI on my own machineRepo

tessera

From teacher to tiles — 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.

  • 556
  • Python
  • 6 wk ago
zengxiao-heTake it
GitHubRepo

awesome-mechanistic-interpretability

A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components.

  • 179
  • JavaScript
  • 3 d ago
Search GitHub and Hugging Face for mechanistic-interpretability

Get , open it once and sign in. Then come back here and press the button again.