Reading up on Chris Olah
3 deep · digging since feb 11
- God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques
The article surveys mechanistic interpretability methods—linear probes, sparse autoencoders, activation verbalizers, emotion probes, Jacobians—and discusses their strengths, limitations, and recent setbacks in real language models.
- What Is Claude? Anthropic Doesn’t Know, Either
Anthropic researchers use interpretability methods to study Claude's internal workings, finding its selfhood is shaped by both neurons and narratives like human minds.