Pearce, Michael T

6 publications

ICLR 2025 Bilinear MLPs Enable Weight-Based Mechanistic Interpretability Michael T Pearce, Thomas Dooms, Alice Rigg, Jose Oramas, Lee Sharkey

ICLR 2025 Sparse Autoencoders Do Not Find Canonical Units of Analysis Patrick Leask, Bart Bussmann, Michael T Pearce, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Lee Sharkey, Neel Nanda

NeurIPSW 2024 Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations Kola Ayonrinde, Michael T Pearce, Lee Sharkey

NeurIPSW 2024 Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations Kola Ayonrinde, Michael T Pearce

NeurIPSW 2024 Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations Kola Ayonrinde, Michael T Pearce, Lee Sharkey

ICMLW 2024 Weight-Based Decomposition: A Case for Bilinear MLPs Michael T Pearce, Thomas Dooms, Alice Rigg