https://openreview.net/forum?id=a98SfVkYRk&referrer=%5Bthe%20profile%20of%20Chun%20Hei%20Yip%5D(%2Fprofile%3Fid%3D~Chun_Hei_Yip1)
Feature interactions in sparse crosscoders from compact proofs | OpenReview
Dictionary learning methods like Sparse Autoencoders (SAEs) and crosscoders attempt to explain a model by decomposing its activations into independent...
featureinteractionssparsecompactproofs