Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Audio is streamed directly from the publisher (media.transistor.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
🤗 Upvotes: 41 | cs.LG, cs.CL
Authors:
Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov
Title:
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Arxiv:
http://arxiv.org/abs/2502.03032v2
Abstract:
We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine similarity technique, we trace how specific features persist, transform, or first appear at each stage. This method yields granular flow graphs of feature evolution, enabling fine-grained interpretability and mechanistic insights into model computations. Crucially, we demonstrate how these cross-layer feature maps facilitate direct steering of model behavior by amplifying or suppressing chosen features, achieving targeted thematic control in text generation. Together, our findings highlight the utility of a causal, cross-layer interpretability framework that not only clarifies how features develop through forward passes but also provides new means for transparent manipulation of large language models.