Patrick Leask

Within this scope...

subprojects

• 16 Jul 2025

  Latent mechanistic interpretability

timeline

• Conference poster

  16 Jul 2025

  Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models

• Public symposium

  2 Jul 2025

  Interpreting intelligent machines?

• Paper & Poster

  24 Apr 2025

  Sparse Autoencoders Do Not Find Canonical Units of Analysis

• Conference poster

  15 Dec 2024

  BatchTopK Sparse Autoencoders

• Conference poster

  15 Dec 2024

  Stitching Sparse Autoencoders of Different Sizes

• Analysis

  17 Aug 2024

  Calendar feature geometry in GPT-2 layer 8 residual stream SAEs

• Workshop

  6 May 2024

  AI Forensics IRL Meeting

• Preprint

  1 Nov 2023

  CoinRun: Solving Goal Misgeneralisation