Skip to content
conftrace_
2025 ICML ICML 2025

Analyze Feature Flow to Enhance Interpretation and Steering in 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

Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov

Topics

Artificial Intelligence > Core AI > Interpretability Natural Language Processing > Generation > Language Modeling Artificial Intelligence > Core AI > Large Language Models

Keywords

sparse autoencoder cosine similarity large language model feature flow steering cross-layer feature maps
Download PDF