Toward universal steering and monitoring of AI models
Computer Science and Engineering(计算机科学与工程);Broad Institute of MIT and Harvard(MIT和哈佛大学Broad研究所);UC San Diego(圣地亚哥大学);Harvard SEAS(哈佛大学工程与应用科学学院);MIT Mathematics(MIT数学系);Halıcıoğlu Data Science Institute(Halıcıoğlu数据科学研究所);Harvard CMSA(哈佛大学计算机科学与应用数学系)
Daniel Beaglehole, Adityanarayanan Radhakrishnan, Enric Boix-Adserà, Mikhail Belkin
Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model capabilities and development of effective safeguards. Building on recent advances in feature learning, we develop an effective, scalable approach for extracting linear representations of general concepts in large-scale AI models (language models, vision-language models, and reasoning models). We show how these representations enable model steering, through which we expose vulnerabilities, mitigate misaligned behaviors, and improve model capabilities. Additionally, we demonstrate that concept representations are remarkably transferable across human languages and combinable to enable multi-concept steering. Through quantitative analysis across hundreds of concepts, we find that newer, larger models are more steerable and steering can improve model capabilities beyond standard prompting. We show how concept representations are effective for monitoring misaligned content (hallucinations, toxic content). We demonstrate that predictive models built using concept representations are more accurate for monitoring misaligned content than using models that judge outputs directly. Together, our results illustrate the power of using internal representations to map the knowledge in AI models, advance AI safety, and improve model capabilities.
Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models
University of Zurich and University Hospital of Zurich(苏黎世大学及苏黎世大学医院);Kobe University(Kobe大学);ETH AI Center(苏黎世联邦理工学院人工智能中心);ETH Zurich(苏黎世联邦理工学院);Stanford University(斯坦福大学);Zurich University of Applied Sciences(苏黎世应用科学大学)
When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
State Key Laboratory of Multimedia Information Processing, Peking University(北京大学多媒体信息处理国家重点实验室);School of Computer Science, Peking University(北京大学计算机科学学院)