Vadim21221/saes
Updated
Vadim Kurochkin
Vadim21221
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
21 days ago
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
upvoted
a
paper
about 2 months ago
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story
upvoted
a
paper
about 2 months ago
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Organizations
None yet
Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_131072_mul_fractal_jumprelu
Updated
Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_65536_jumprelu
Updated
Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_65536_mul_fractal_jumprelu
Updated
Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_131072_jumprelu
Updated
Vadim21221/sae__mount_path_qwen2.5-7b_resid_post_layer_14_size_163840_mul_fractal_topk
Updated
Vadim21221/sae__mount_path_qwen2.5-7b_resid_post_layer_14_size_163840_topk
Updated
Vadim21221/sae_EleutherAI_pythia-1.4b_resid_post_layer_12_size_65536_topk
Updated
Vadim21221/sae_EleutherAI_pythia-1.4b_resid_post_layer_12_size_65536_mul_fractal_topk
Updated
Vadim21221/sae_google_gemma-2-2b_resid_post_layer_12_size_65536_mul_fractal_topk
Updated
Vadim21221/sae_google_gemma-2-2b_resid_post_layer_12_size_65536_topk
Updated
Vadim21221/sae_google_gemma-2b_resid_post_layer_12_size_65536_topk
Updated
Vadim21221/sae_EleutherAI_pythia-70m_resid_post_layer_3_size_262144_mul_fractal_topk
Updated
Vadim21221/sae_google_gemma-2b_resid_post_layer_12_size_65536_mul_fractal_topk
Updated
Vadim21221/Llama-3.2-1B-Instruct_full_lora
Updated
Vadim21221/Llama-3.2-1B-Instruct_all_mlp
Updated
Vadim21221/Qwen2.5-1.5B-Instruct_all_mlp
Updated
Vadim21221/Qwen2.5-1.5B-Instruct_new_sae_init
Updated
Vadim21221/qwen2_1_5b-instruct-layerwise-sae_new_sae_init
Text Generation
•
2B
•
Updated
•
1
Vadim21221/qwen2_1_5b-instruct-layerwise-sae_lr_1e_7
Text Generation
•
2B
•
Updated
•
1
Vadim21221/Qwen2.5-1.5B-Instruct
Text Generation
•
2B
•
Updated
•
7
Vadim21221/qwen2_1_5b-instruct-steering-vectorsteeringxlora
Text Generation
•
2B
•
Updated
•
1
Vadim21221/qwen2_1_5b-instruct-layerwise-saesteeringxlora
Updated
Vadim21221/qwen2_1_5b-instruct-steering-vector
Text Generation
•
2B
•
Updated
•
1
Vadim21221/Qwen2-0.5B-GRPO-demo
Updated
Vadim21221/Qwen2-0.5B-GRPO-test
Updated
Vadim21221/q-taxi
Reinforcement Learning
•
Updated
Vadim21221/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning
•
Updated
Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_12_size_16384_topk_reg_coeff_0.0018
Updated
Vadim21221/sae_Qwen_Qwen2.5-1.5B-Instruct_resid_post_layer_12_size_16384_topk_reg_coeff_0.0018
Updated