AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Jesse Hoogland on Developmental Interpretability and Singular Learning Theory
The Inside View
The Effects of Face Transitions on Neural Networks
In a magnet, you only need an infinitesimally small perturbation to that system in order to point it in a certain direction. And so if you bring this back to neural networks, if the weights are slightly different, the overall model could be like the sepsilon or not. So there are these toy models of superposition studied by anthropic. You can see that the way compresses data involves this kind of symmetry breaking and selects one solution out of phase transition.
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