אטלסי תכונות ייחוס לביקורת מנגנונית של מודלי שפה

תקציר מקורי באנגליתarXiv:2607.22570v1 Announce Type: new Abstract: Auditing a new language model usually means relearning and reinterpreting its internal features from scratch. We propose a reference feature atlas: a sparse feature library trained once on a reference panel and reused for new targets, which attach by fitting only a linear decoder. This yields two complementary views. The atlas channel reads the target on already interpreted panel features, providing a stable coordinate system across models. The residual channel learns features only from what the atlas fails to reconstruct, making "outside the reference panel" an explicit audit signal. We train leave-one-out atlases over five 7-9B instruction-tuned models and audit held-out Mistral and Qwen targets. On three controlled LoRA hidden objectives i