jacobcd52/roneneldan_TinyStories-1M_transformer.h.0.attn.attention.v_proj.weight_sae_k16 Updated Jun 26
jacobcd52/pythia-70m_warmup0.3_k16_mask3e-05_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 7 • 2
jacobcd52/pythia-70m_warmup0.3_k16_mask0.0001_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 7 • 2
jacobcd52/pythia-70m_warmup0.3_k16_mask0.001_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 6 • 2
jacobcd52/pythia-70m_warmup0.3_k16_mask0.01_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 5 • 2
jacobcd52/pythia-70m_warmup0.3_k16_mask0.0003_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 4 • 2
jacobcd52/pythia-70m_allstart_k16_mask0.0001_fact_fvu0.1_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 3 • 2
jacobcd52/pythia-70m_allstart_k16_mask0.001_fact_fvu0.1_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 3 • 3
jacobcd52/pythia-70m_allstart_k16_mask0.001_fact_fvu0.2_fvu_sparse1.0_fvu1.0_lr0.0005 Updated Jun 3 • 2