Atlas-Alignment: Making Interpretability Transferable Across Language Models

arXiv:2510.27413v2 Announce Type: replace-cross
Abstract: Interpretability is crucial for building safe, reliable, and controllable language models, yet existing interpretability pipelines remain costly and difficult to scale. Interpreting a new model typically requires training model-specific components (e.g., sparse autoencoders), followed by manual or semi-automated labeling and validation, imposing a growing “transparency tax” that does not scale with the pace of model development. We introduce Atlas-Alignment, a framework that avoids this cost by aligning the latent space of a new model to a pre-existing, labeled Concept Atlas using only shared inputs and lightweight representational alignment methods. Through quantitative and qualitative evaluations, we show that simple alignment methods enable robust semantic retrieval and steerable generation without the need for labeled concept datasets. Atlas-Alignment thus amortizes the cost of explainable AI and mechanistic interpretability: by investing in a single high-quality Concept Atlas, we can make many new models transparent and controllable at minimal marginal cost.