arxiv:2502.09245
Gleb Gerasimov
gudleifrr
·
AI & ML interests
NLP, interpretability
Recent Activity
updated
a model
1 day ago
gudleifrr/gpt2_saes
updated
a model
1 day ago
gudleifrr/gpt2_saes
updated
a model
1 day 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
•
10
gudleifrr/interpretations
Updated
•
7
gudleifrr/OpenThoughts-114k-full-fix
Viewer
•
Updated
•
114k
•
17
gudleifrr/steering_diff
Preview
•
Updated
•
149
gudleifrr/MATH-500
Viewer
•
Updated
•
500
•
4
gudleifrr/OpenThoughts-114k-full
Viewer
•
Updated
•
114k
•
11
gudleifrr/linear_probing
Viewer
•
Updated
•
8
•
20
gudleifrr/OpenThoughts-114k-thinking
Viewer
•
Updated
•
114k
•
15
gudleifrr/text-correction-en
Viewer
•
Updated
•
784k
•
6