Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov
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.
BibTeX
@inproceedings{
laptev2025analyze,
title={Analyze Feature Flow to Enhance Interpretation and Steering in Language Models},
author={Daniil Laptev and Nikita Balagansky and Yaroslav Aksenov and Daniil Gavrilov},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=SENVTfjHPr}
}