Andrey Galichin

andreuka18

avgalichin

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

andreuka18/DeepSeek-R1-Distill-Llama-8B-lmsys-openthoughts-tokenized:Add dataset description, paper link, task category, and code link

new activity 3 days ago

andreuka18/OpenThoughts-10k-DeepSeek-R1:Add link to paper and description

new activity 3 days ago

andreuka18/deepseek-r1-distill-llama-8b-lmsys-openthoughts:Add/improve metadata: pipeline tag, license, link to paper and code

View all activity

Organizations

None yet

andreuka18's activity

New activity in andreuka18/DeepSeek-R1-Distill-Llama-8B-lmsys-openthoughts-tokenized 3 days ago

Add dataset description, paper link, task category, and code link

#2 opened 4 days ago by

nielsr

New activity in andreuka18/OpenThoughts-10k-DeepSeek-R1 3 days ago

Add link to paper and description

#1 opened 4 days ago by

nielsr

New activity in andreuka18/deepseek-r1-distill-llama-8b-lmsys-openthoughts 3 days ago

Add/improve metadata: pipeline tag, license, link to paper and code

#1 opened 4 days ago by

nielsr

updated a collection 3 days ago

SAE-Reasoning

Collection

Models and datasets used in the paper "Interpreting Reasoning Features in Large Language Models via Sparse Autoenoder": https://arxiv.org/abs/2503.188 • 4 items • Updated 3 days ago

updated a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-lmsys-openthoughts-tokenized

Viewer • Updated 4 days ago • 781k • 173

published a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-lmsys-openthoughts-tokenized

Viewer • Updated 4 days ago • 781k • 173

updated a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-OpenThoughts-114k-tokenized

Updated 4 days ago • 217

published a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-OpenThoughts-114k-tokenized

Updated 4 days ago • 217

updated a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-lmsys-chat-1m-tokenized

Viewer • Updated 4 days ago • 486k • 190

published a dataset 4 days ago

andreuka18/DeepSeek-R1-Distill-Qwen-7B-lmsys-chat-1m-tokenized

Viewer • Updated 4 days ago • 486k • 190

authored a paper 6 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 10 days ago • 110

updated a collection 8 days ago

SAE-Reasoning

Collection

Models and datasets used in the paper "Interpreting Reasoning Features in Large Language Models via Sparse Autoenoder": https://arxiv.org/abs/2503.188 • 4 items • Updated 3 days ago

upvoted a paper 9 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 10 days ago • 110

updated a dataset 11 days ago

andreuka18/SimpleQA-1000

Updated 11 days ago • 26

published a dataset 11 days ago

andreuka18/SimpleQA-1000

Updated 11 days ago • 26

updated a model 24 days ago

andreuka18/deepseek-r1-distill-llama-8b-openthoughts

Updated 24 days ago

published a model 24 days ago

andreuka18/deepseek-r1-distill-llama-8b-openthoughts

Updated 24 days ago

updated a model 24 days ago

andreuka18/deepseek-r1-distill-llama-8b-lmsys-openthoughts

Text Generation • Updated 3 days ago