BlueDot Narrated cover image

Introduction to Mechanistic Interpretability

BlueDot Narrated

00:00

Early feature steering results

Perrin Walker notes attempts to weaken or amplify features to influence model outputs, with playful examples.

Play episode from 11:14
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