The research community is just trying to improve this frontier of getting better and better at explaining harder behaviors but in a more zoomed in way. Like a neuron level explanations of how like toy transformers complete the correct completion to like modular addition which is worked by neo-nanda and collaborators. We have much worse understanding but still some understanding of how gpt too small like completes its predictions that solely in terms of like attention heads and MLPs.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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