"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

E48: Mechanizing Mechanistic Interpretability with Arthur Conmy

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

00:00

Understanding Mechanistic Interpretability in AI

This chapter delves into the mechanistic interpretability workflow in AI, laying out a three-step process for understanding neural network behaviors. The speakers discuss the challenges involved and the potential for automation to streamline the discovery of critical components.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app