Edit Models filters

stable-baselines3

sentence-transformers

Transformers.js

Models

185

Full-text search

Active filters: saelens

suchitg/sae-compression-gpt-2-small-pruned-sae-pile_0.25

suchitg/sae-compression-gpt-2-small-pruned-sae-openwebtext_0.75

ElectronicRain/sae-train_gpt2-large

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha1

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha20

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha5

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha0.01

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha0.00086

NoamDiamant52/model_gpt2-xl_mlp_out_lr5e5_steps45k_alpha0.1

chanind/sae-llama-3.2-1b-topk-res

chanind/sae-llama-3.2-1b-res-random-baseline

NoamDiamant52/model_QWEN2_mlp_out_lr5e5_steps45k_alpha5

seonglae/gemma-2-2b-sae

seonglae/Llama-3.2-3B-sae

seonglae/Llama-3.2-1B-sae

seonglae/Llama-3.1-8B-sae

andreuka18/sae-deepseek-r1-llama-8b

NoamDiamant52/model_QWEN2_mlp_out_lr5e5_steps45k_alpha4

anhtu77/sae-gpt2-small

kkkarnav/sae_gpt2

kkkarnav/sae_gpt2_gab

suchitg/llama_scope_lxr_8x_8bit

suchitg/llama_scope_lxr_8x

suchitg/llama_scope_lxa_8x_8bit

darpanaswal/TER-SAEs

suchitg/llama_scope_lxa_8xq

suchitg/llama_scope_lxr_8x_8W16A

suchitg/llama_scope_lxa_8x_8W16A

suchitg/llama_scope_lxm_8x_8W16A

andreuka18/sae-slimpajama-deepseek-r1-llama-8b