Alexey Dontsov's picture

Alexey Dontsov

therem

·

somvy

AI & ML interests

None yet

Recent Activity

liked a model 5 days ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

updated a dataset 10 days ago

therem/novel-ops-impossible

published a dataset 10 days ago

therem/novel-ops-impossible

View all activity

Organizations

authored a paper 29 days ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 56

submitted a paper to Daily Papers 29 days ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 56

authored a paper 5 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 19

authored a paper 6 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28

authored a paper 12 months ago

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

Paper • 2503.18878 • Published Mar 24, 2025 • 119