AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
14min chapter
Sholto Douglas & Trenton Bricken - How to Build & Understand GPT-7's Mind
Dwarkesh Podcast
Unraveling the Nuances of Model Learning and Interpretation
Delve into the intricacies of GPT-7's predictive capabilities with a focus on base 64 encodings, showcasing dense representations for token prediction. Explore anomaly detection through dictionary learning, highlighting challenges in interpreting complex models and scaling feature labeling. Discuss the interplay of capacity in model learning using bird features as an example, emphasizing the importance of understanding neural connections, weights, and feature extraction in model interpretation.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode