Visualizing LLM Latent Space Geometry Through Dimensionality Reduction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912801358872576 |
|---|---|
| author | Ning, Alex Rangaraju, Vainateya Kuo, Yen-Ling |
| author_facet | Ning, Alex Rangaraju, Vainateya Kuo, Yen-Ling |
| contents | Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings and the sequence-wise geometric patterns in LLaMa. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Visualizing LLM Latent Space Geometry Through Dimensionality Reduction Ning, Alex Rangaraju, Vainateya Kuo, Yen-Ling Machine Learning Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings and the sequence-wise geometric patterns in LLaMa. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization. |
| title | Visualizing LLM Latent Space Geometry Through Dimensionality Reduction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.21594 |