← 研踪 PaperTrailarXiv:2611.01378 · v1
Information-Theoretic Design of Sparse Autoencoder-Based Steering
首次提交 2026-11-01 08:33
版本更新 2026-11-01 08:33
雷达观测 2026-11-04 23:43
摘要
Sparse autoencoder (SAE)-based activation steering is a lightweight approach for modifying the behavior of large language models (LLMs) by adding small vectors to hidden states during inference. However, designing effective steering interventions remains challenging. In this work, we develop an information-theoretic framework for analyzing SAE activations through empirical feature-firing distributions. The central object of the framework is the Jensen--Shannon divergence (JSD) between such firing distributions, which quantifies how far a generated or intervened state deviates from a dataset-induced target distribution. Based on an analytic divergence response for virtually shifted states, we construct steering vectors toward the target firing distribution. The same divergence can also be used to monitor deviation from another empirical distribution, such as a general valid-language distribution. We demonstrate the effectiveness of the steering in a question-mode generation task study. We further use teacher-forced pulse experiments to show that local interventions induce structured downstream JSD responses in later layers, and apply the framework to a safety-related target--contrast response setting for feature analysis.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-01 08:33 · 最新观测版本
Information-Theoretic Design of Sparse Autoencoder-Based Steering
Sparse autoencoder (SAE)-based activation steering is a lightweight approach for modifying the behavior of large language models (LLMs) by adding small vectors to hidden states during inference. However, designing effective steering interventions remains challenging. In this work, we develop an information-theoretic framework for analyzing SAE activations through empirical feature-firing distributions. The central object of the framework is the Jensen--Shannon divergence (JSD) between such firing distributions, which quantifies how far a generated or intervened state deviates from a dataset-induced target distribution. Based on an analytic divergence response for virtually shifted states, we construct steering vectors toward the target firing distribution. The same divergence can also be used to monitor deviation from another empirical distribution, such as a general valid-language distribution. We demonstrate the effectiveness of the steering in a question-mode generation task study. We further use teacher-forced pulse experiments to show that local interventions induce structured downstream JSD responses in later layers, and apply the framework to a safety-related target--contrast response setting for feature analysis.
查看此版本解读 →查看此版本原文 ↗