Nikita Balagansky

elephantmipt's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 1 day ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published 8 days ago • 28 •

3

authored a paper 2 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published 8 days ago • 28

upvoted a paper 2 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published 8 days ago • 28

authored a paper 14 days ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published 16 days ago • 55

upvoted a paper 16 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 18 days ago • 111

updated 9 models about 1 month ago

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_24_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024 • 36

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_18_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_12_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_12_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_24_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024 • 36

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_18_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_12_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_24_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024 • 36

elephantmipt/sae_Qwen_Qwen2.5-7B_resid_pre_layer_18_size_16384_batchtopk_reg_coeff_0.0018

Updated Dec 29, 2024