Vadim Kurochkin

Vadim21221 's models 31

Sort:  Recently updated

Vadim21221/saes

Updated Jul 30

Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_131072_mul_fractal_jumprelu

Updated Jul 29 • 12

Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_65536_jumprelu

Updated Jul 29 • 11

Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_65536_mul_fractal_jumprelu

Updated Jul 29 • 14

Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_14_size_131072_jumprelu

Updated Jul 29 • 12

Vadim21221/sae__mount_path_qwen2.5-7b_resid_post_layer_14_size_163840_mul_fractal_topk

Updated Jul 29 • 6

Vadim21221/sae__mount_path_qwen2.5-7b_resid_post_layer_14_size_163840_topk

Updated Jul 29 • 12

Vadim21221/sae_EleutherAI_pythia-1.4b_resid_post_layer_12_size_65536_topk

Updated Jul 29 • 11

Vadim21221/sae_EleutherAI_pythia-1.4b_resid_post_layer_12_size_65536_mul_fractal_topk

Updated Jul 29 • 11

Vadim21221/sae_google_gemma-2-2b_resid_post_layer_12_size_65536_mul_fractal_topk

Updated Jul 29 • 8

Vadim21221/sae_google_gemma-2-2b_resid_post_layer_12_size_65536_topk

Updated Jul 29 • 6

Vadim21221/sae_google_gemma-2b_resid_post_layer_12_size_65536_topk

Updated Jul 28 • 21

Vadim21221/sae_EleutherAI_pythia-70m_resid_post_layer_3_size_262144_mul_fractal_topk

Updated Jul 28 • 13

Vadim21221/sae_google_gemma-2b_resid_post_layer_12_size_65536_mul_fractal_topk

Updated Jul 28 • 20

Vadim21221/Llama-3.2-1B-Instruct_full_lora

Updated Jul 15

Vadim21221/Llama-3.2-1B-Instruct_all_mlp

Updated Jul 15

Vadim21221/Qwen2.5-1.5B-Instruct_all_mlp

Updated Jul 15

Vadim21221/Qwen2.5-1.5B-Instruct_new_sae_init

Updated Jul 14

Vadim21221/qwen2_1_5b-instruct-layerwise-sae_new_sae_init

Text Generation • 2B • Updated Jul 14 • 6

Vadim21221/qwen2_1_5b-instruct-layerwise-sae_lr_1e_7

Text Generation • 2B • Updated Jul 13

Vadim21221/Qwen2.5-1.5B-Instruct

Text Generation • 2B • Updated Jul 13 • 3

Vadim21221/qwen2_1_5b-instruct-steering-vectorsteeringxlora

Text Generation • 2B • Updated Jul 13 • 3

Vadim21221/qwen2_1_5b-instruct-layerwise-saesteeringxlora

Updated Jul 13

Vadim21221/qwen2_1_5b-instruct-steering-vector

Text Generation • 2B • Updated Jul 13 • 3

Vadim21221/Qwen2-0.5B-GRPO-demo

Updated Jul 12

Vadim21221/Qwen2-0.5B-GRPO-test

Updated Jul 12

Vadim21221/q-taxi

Reinforcement Learning • Updated Jul 5

Vadim21221/q-FrozenLake-v1-4x4-noSlippery

Reinforcement Learning • Updated Jul 5

Vadim21221/sae_Qwen_Qwen2.5-1.5B_resid_post_layer_12_size_16384_topk_reg_coeff_0.0018

Updated Jun 10

Vadim21221/sae_Qwen_Qwen2.5-1.5B-Instruct_resid_post_layer_12_size_16384_topk_reg_coeff_0.0018

Updated Jun 10