BlueDot Narrated cover image

Introduction to Mechanistic Interpretability

BlueDot Narrated

00:00

Intervening in model processes

Perrin Walker discusses isolating harmful parts of networks and feature steering to modify outputs.

Play episode from 02:49
Transcript

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