Patrick Leask — accepted AI-conference papers

2025

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

Patrick Leask, Neel Nanda, Noura Al Moubayed

ICML 2025poster

Sparse Autoencoders (SAEs) are a popular method for decomposing Large Language Model (LLM) activations into interpretable latents, however they have a substantial training cost and SAEs learned on different models are not directly comparable. Motivated by relative representation similarity measures,…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

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 +2

ICLR 2025poster

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these features in LLMs, and it has been postulated that they can be…

Cited by 1 Source ↗PDF ↗Scholar ↗