Skip to content

David Bau: Interpretability and model editing

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

Model interpretability and automated editing techniques in neural networks are taught by Bau. An 84-minute technical lecture covers methods for understanding and modifying AI models.

Video by UC Berkeley EECS, played through YouTube's embedded player.

Part of Understanding Large Language Models: Foundations and Safety