publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. jsaes.png
    Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
    Lucy Farnik, Tim Lawson, Conor Houghton, and 1 more author
    In Forty-second International Conference on Machine Learning, 2025
    arXiv
  2. mlsaes.png
    Residual Stream Analysis with Multi-Layer SAEs
    Tim Lawson, Lucy Farnik, Conor Houghton, and 1 more author
    In The Thirteenth International Conference on Learning Representations, 2025
    arXiv
  3. random_saes.png
    Sparse Autoencoders Can Interpret Randomly Initialized Transformers
    Thomas Heap, Tim Lawson, Lucy Farnik, and 1 more author
    2025
    arXiv

2024

  1. starc.png
    STARC: A General Framework For Quantifying Differences Between Reward Functions
    Joar M. V. Skalse, Lucy Farnik, Sumeet R. Motwani, and 3 more authors
    In The Twelfth International Conference on Learning Representations, 2024
    arXiv
  2. fmri_finetuning.png
    Inducing Human-like Biases in Moral Reasoning Language Models
    Austin Meek, Artem Karpov, Seong H. Cho, and 3 more authors
    In UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models, 2024
    arXiv