vix.ing · top · new · best · stats · spec

Hoogland, Jesse

  1. Open Problems in Mechanistic Interpretability
    2025/01/27 by Lee Sharkey, Bilal Chughtai, Sharkey, Lee +58 · 7 voices · 40 citations
    Computer Science · #Natural Language Processing Techniques #Statistical and Computational Modeling #cs.LG
  2. Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
    2024/10/03 by Wang, George, Hoogland, Jesse, van Wingerden, Stan +2 · 11 citations
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
  3. You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
    2025/02/08 by Lehalleur, Simon Pepin, Hoogland, Jesse, Farrugia-Roberts, Matthew +5 · 6 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG)
  4. Loss Landscape Degeneracy and Stagewise Development in Transformers
    2024/02/04 by Hoogland, Jesse, Wang, George, Farrugia-Roberts, Matthew +3 · 3 citations
    #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
  5. Dynamics of Transient Structure in In-Context Linear Regression Transformers
    2025/01/29 by Carroll, Liam, Hoogland, Jesse, Farrugia-Roberts, Matthew +1 · 5 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG)
  6. Structural Inference: Interpreting Small Language Models with Susceptibilities
    2025/04/25 by Garrett Baker, George Wang, Baker, Garrett +5 · 2 voices · 2 citations
    Computer Science · #Natural Language Processing Techniques #Topic Modeling