Hello!

I’m a neural network interpretability researcher interested in unsupervised methods and agency.

I like to train strange sparse autoencoders, most recently binary TopK autoencoders (BAEs) and TopK SAEs trained on backward pass gradients. At the moment I’m thinking about using the board game Diplomacy as a testbed for studying strategic interactions in multi-agent environments.

Github: https://github.com/luciaquirke

Twitter: https://twitter.com/lucia_quirke