Skip to main content

Danbraunai-apollo's workspace

200,000220,000240,000260,000280,000300,000320,000340,000360,000380,000400,000n_samples
100200300400500600700sparsity/eval/L_0/blocks.6.hook_resid_pre-1-0.9-0.8-0.7-0.6-0.5-0.4-0.3-0.2-0.1performance/eval/difference_ce_loss