PPaperPicks

Anton Razzhigaev

5 papers at tracked venues · 3 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
  2. Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
  3. LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
    NAACL 2025 · Anton Razzhigaev
  4. Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images
  5. Your Transformer is Secretly Linear
    ACL 2024 · Anton Razzhigaev