Skip to content
conftrace_
2025 ICML ICML 2025

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

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Patrick Leask, Neel Nanda, Noura Al Moubayed

Topics

Artificial Intelligence > Core AI > Foundation Models Artificial Intelligence > Core AI > Interpretability Natural Language Processing > Resources & Methods > Large Language Models

Keywords

sparse autoencoder inference time representation similarity activation decomposition dictionary
Download PDF