arxiv:2502.09245
Gleb Gerasimov
gudleifrr
AI & ML interests
NLP, interpretability
Recent Activity
liked
a Space 3 days ago
t-tech/manifolds upvoted a paper 14 days ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare updated
a model about 1 month ago
gudleifrr/gpt2_saes Organizations
None yet
models 214
gudleifrr/gpt2_saes
Updated
gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.15.hook_resid_post_16384_batchtopk_64_0.001_9715
Updated
gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_1376
Updated
gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_3866
Updated
gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_9689
Updated
gudleifrr/sae_Qwen_Qwen2.5-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_8634
Updated
gudleifrr/sae_Qwen_Qwen2.5-Math-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_r1
Updated
gudleifrr/sae_Qwen_Qwen2.5-7B_diff_blocks.10.hook_resid_post_16384_batchtopk_64_0.001_r1
Updated
gudleifrr/sae_Qwen_Qwen2.5-7B_default_ln_final.hook_normalized_16384_batchtopk_64_0.001
Updated
gudleifrr/sae_Qwen_Qwen2.5-7B_default_blocks.10.hook_resid_post_16384_batchtopk_64_0.001
Updated
datasets 9
gudleifrr/gpt2_saes
Updated
• 5
gudleifrr/interpretations
Updated
• 8
gudleifrr/OpenThoughts-114k-full-fix
Viewer
• Updated
• 114k • 10
gudleifrr/steering_diff
Preview
• Updated
• 2.42k
gudleifrr/MATH-500
Viewer
• Updated
• 500 • 3
gudleifrr/OpenThoughts-114k-full
Viewer
• Updated
• 114k • 11
gudleifrr/linear_probing
Viewer
• Updated
• 8 • 2
gudleifrr/OpenThoughts-114k-thinking
Viewer
• Updated
• 114k • 11
gudleifrr/text-correction-en
Viewer
• Updated
• 784k • 2