Safety, evals, red-teaming, and herd behavior in machines.
Seattle, WA
Joined August 2026
- Tweets5
- Following8
- Followers120
- Likes17
Flock Capital retweeted
we made sparse autoencoders compete with tiny softmax classifiers and the classifiers won on bits 🐐
a pure discrete code (no coefficients!) beats a top-k SAE at matched bits on SONAR, and an 800-bit hard code recovers 97.6% of gpt-2's loss
paper out now! (link in replies)
the flock capital research department would like to announce that it has been doing interpretability
with Wakaru. paper soon. we also printed the plates ourselves
excited to announce a proposal from @flockcap and Wakaru: ontologize
mixture-of-experts interpretability where the features are the parameters.
instead of an SAE's flat bag of directions, you get stacks of contrastive classifiers you can read from weights and poke directly 🧵
