Mechanistic Interpretability - NEEL NANDA (DeepMind)

http://80000hours.org/mlst
Visit our sponsor 80000 hours - grab their free career guide and check out their podcast! Use our special link above!

Support us! https://www.patreon.com/mlst
MLST Discord: https://discord.gg/aNPkGUQtc5
Twitter: https://twitter.com/MLStreetTalk

In this wide-ranging conversation, Tim Scarfe interviews Neel Nanda, a researcher at DeepMind working on mechanistic interpretability, which aims to understand the algorithms and representations learned by machine learning models. Neel discusses how models can represent their thoughts using motifs, circuits, and linear directional features which are often communicated via …

algorithms career check conversation deepmind free guide interpretability interviews machine machine learning machine learning models podcast researcher