philpaxMechanistic Interpretability
- TMS & SAE Exercises
- 200 Concrete Open Problems in Mechanistic Interpretability: Introduction
- Concrete Steps to Get Started in Transformer Mechanistic Interpretability
- A Comprehensive Mechanistic Interpretability Explainer & Glossary
- [Summary] Progress Update #1 from the GDM Mech Interp Team
- An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability
- SAE feature geometry is outside the superposition hypothesis
- Mapping the latent space of Llama 3.3 70B
- Painting with concepts