Inside the Black Box: Cracking AI and Deep Learning

Decoding GPTs Hidden Circuits


Listen Later

Explore how sparse autoencoders and transcoders unveil the inner workings of GPT-2 by revealing functional features and computational circuits. Discover breakthrough methods that shift from observing raw network activations to mapping the model's actual computation, making AI behavior more interpretable than ever.
...more
View all episodesView all episodes
Download on the App Store

Inside the Black Box: Cracking AI and Deep LearningBy Jellypod