Skip to main content

GPT2 layerwise vs e2e SAEs (currently only layerwise)

Created on March 28|Last edited on March 28

Section 1


102030405060708090loss.sparsity.coeff
100200300400500600700sparsity/eval/L_0/blocks.2.hook_resid_pre-0.7-0.6-0.5-0.4-0.3-0.2-0.1performance/eval/difference_ce_loss
Run set
299


Fixed dictionary size, vary sparsity penalty


Run set
299