There's a good distinction here between two ways in which we like tested the AC-DC algorithm that involved like validation tests. In this case you're not so worried about the sweep over all possible parameters you're looking for Like a revealing subgraph which helps you begin your research into how the model is doing a particular task. I think there's like two modes there that like in the work in machine learning work you need to like validate that like actually your technique is helpful for recovering circuits but then in practice you can do like a really stopping essentially once you found something which is revealing how models do certain tasks yeah.

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