Machine Learning Street Talk (MLST) cover image

Neel Nanda - Mechanistic Interpretability (Sparse Autoencoders)

Machine Learning Street Talk (MLST)

00:00

Intro

This chapter focuses on the significance of sparse autoencoders and mechanistic interpretability in enhancing AI safety. It addresses the complexities of machine learning models and their potential implications for existential risks, emphasizing the need for understanding AI behaviors such as planning and deception.

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