AI RESEARCH
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
arXiv CS.LG
•
ArXi:2605.12714v1 Announce Type: new Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representation Dynamics (LRD), a framework with three layer-wise measurement families: Frenet (Grassmann speed and curvature) for global subspace motion, Neighborhood Retention Score (NRS) for local nearest-neighbor retention, and Graph Filtration Mutual Information (GFMI) for alignment with the final layer.