Gleb Gerasimov's picture

8 1

Gleb Gerasimov

gudleifrr

·

humdinger-g

AI & ML interests

NLP, interpretability

Organizations

None yet

gudleifrr 's models 214

gudleifrr/gpt2_saes

gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.15.hook_resid_post_16384_batchtopk_64_0.001_9715

Updated Aug 25, 2025

gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_1376

Updated Aug 25, 2025

gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_3866

Updated Aug 25, 2025

gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_9689

Updated Aug 21, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_8634

Updated Aug 21, 2025

gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_r1

Updated Aug 21, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_r1

Updated Aug 21, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_default_ln_final.hook_normalized_16384_batchtopk_64_0.001

Updated Aug 15, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_default_blocks.10.hook_resid_post_16384_batchtopk_64_0.001

Updated Aug 15, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001

Updated Aug 15, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_softC_topm20_16384_batchtopk_64_0.001

Updated Aug 14, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_default_blocks.27.hook_resid_post_16384_batchtopk_64_0.001

Updated Aug 14, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B_softdiff_1024_batchtopk_64_0.001

Updated Aug 13, 2025

gudleifrr/Qwen2.5-7B_grpo2

Text Generation • 8B • Updated Aug 13, 2025 • 2

gudleifrr/Qwen2.5-7B_grpo

Text Generation • 8B • Updated Aug 5, 2025 • 2

gudleifrr/sae_Qwen_Qwen2.5-7B_softdiff_16384_batchtopk_64_0.001

Updated Aug 1, 2025

gudleifrr/denseformer_150M_d1_p1_202

Text Generation • 0.2B • Updated Jul 28, 2025 • 2

gudleifrr/denseformer_150M_d2_p2_202

Text Generation • 0.2B • Updated Jul 28, 2025 • 2

gudleifrr/denseformer_746

Text Generation • 11.5k • Updated Jul 27, 2025 • 2

gudleifrr/lime_659

Text Generation • 11.5k • Updated Jul 27, 2025 • 2

gudleifrr/llama_236

Text Generation • 11.5k • Updated Jul 27, 2025 • 2

gudleifrr/sae_Qwen_Qwen2.5-7B-Instruct_default_blocks.19.hook_resid_post_16384_batchtopk_64_0.001

Updated Jul 22, 2025

gudleifrr/sae_Qwen_Qwen2.5-7B-Instruct_default_blocks.14.hook_resid_post_16384_batchtopk_64_0.001

Updated Jul 22, 2025

gudleifrr/sae_dvc4mmiv

Updated Jul 6, 2025

gudleifrr/sae_9cnv7yqb

Updated Jul 6, 2025

gudleifrr/sae_nolq3r1q

Updated Jul 6, 2025

gudleifrr/sae_rit8mi3l

Updated Jul 6, 2025

gudleifrr/sae_nqd8h670

Updated Jul 6, 2025

gudleifrr/sae_qat9uprn

Updated Jul 6, 2025