The logic lens tool projects intermediate states into the decoding layer, revealing what the model is thinking about for the current token prediction. Initially aiming for a simpler solution by linearly decoding future tokens, it was discovered that the process is more complex, with a small set of heads mediating various tasks. The model autonomously communicates task information without explicit instruction, understanding the relationship between demonstrations and labels.

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