Transformer Geometry Observatory TGO-II: Representational Similarity Observatory
While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood. Existing analyses primarily focus on attention mechanisms and downstream performance, leaving the evolution of representation geometry largely unexplored. In this work, we present Transformer Geometry Observatory-II (TGO-II), a representation geometry analysis framework designed to investigate how Transformer representations evolve during supervised training. TGO-II analyzes
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%engineering87/llm-atlas →
- PossiblePossibly related (embedding) · 55%huggingface/transformers →
- PossiblePossibly related (embedding) · 50%Transformer →
- PossiblePossibly related (embedding) · 46%vlm-starter →
- PossiblePossibly related (embedding) · 45%Build your first transformer from scratch →
- LinkedLinked via arxiv author · 85%Kaustubh Kapil →
“Transformer Geometry Observatory TGO-II: Representational Similarity Observatory”
- LinkedLinked via arxiv author · 85%Kishor P. Upla →
“Transformer Geometry Observatory TGO-II: Representational Similarity Observatory”
- PossiblePossibly related (embedding) · 48%pytorch/vision →