Search

Model interpretability and understanding for PyTorch

Interpretability for sequence generation models 🐛 🔍

A library for mechanistic interpretability of GPT-style language models

open source interpretability platform 🧠

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

PyTorch Kolmogorov-Arnold Networks (spline, Legendre, Chebyshev, convolutional) with quantisation, CUDA, and Integrated-Gradients interpretability.

🪄 Interpreto is an interpretability toolbox for LLMs

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.

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.

Companion code for the global workspace interpretability paper