The geometry of hidden representations of large transformer models

Feb-16-2026, 05:43:08 GMT–Neural Information Processing Systems

By analyzing the intrinsic dimension (ID) and neighbor composition, we find that the representations evolve similarly in transformers trained on protein language tasks and image reconstruction tasks.

large language model, machine learning, natural language, (20 more...)

Neural Information Processing Systems

Feb-16-2026, 05:43:08 GMT

Conferences PDF

Country:
- Asia > Taiwan
  - Taiwan Province > Taipei (0.04)
- Europe > Italy
  - Friuli Venezia Giulia > Trieste Province
    - Trieste (0.05)
  - Tuscany > Florence (0.04)
- North America > United States
  - Minnesota > Hennepin County > Minneapolis (0.14)

Genre:
- Research Report > New Finding (0.68)

Industry:
- Health & Medicine > Pharmaceuticals & Biotechnology (0.95)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Neural Networks > Deep Learning (1.00)
      - Statistical Learning (1.00)
    - Natural Language > Large Language Model (1.00)
    - Representation & Reasoning (1.00)
  - Sensing and Signal Processing > Image Processing (0.67)

Duplicate Docs Excel Report

Title
The geometry of hidden representations of large transformer models

Similar Docs Excel Report more

Title	Similarity	Source
None found