Viewing profile — jengels_

Sure, but completeness is a much higher bar than being able to find at least some things we weren’t looking for. And I’m reasonably optimistic that we’re going to make SAEs much be…

It's a super interesting direction! That's one of the long term goals of interp research: deconstruct model behavior into circuits of features, and then turn those circuits into co…

I'm one of the first authors on this paper, happy to answer any questions :)

I feel like un-supurvised methods like Anthropic's SAEs can be argued to find things we're not looking for (their most recent work is from a couple days ago: https://transformer-ci…

Pretty efficient! E.g. a recent paper describes a system to do fully private search over the common crawl (360 million web pages) with an end to end latency of 2.7 seconds: https:/…

Try it out! We have simple scripts you can play with and comparisons with GPT-3.

ThirdAI (thirdai.com) | Houston, Bangalore, or remote | Full time | Senior Software Engineers We are a startup building high performance machine learning systems on CPUs. Our core …

ThirdAI (thirdai.com) | Houston or remote | Full time | Senior Software Engineer, VP Product, VP Engineering We are a startup building hash-based algorithms that accelerate neural …