mlsanityData to 14 Oct 2026

VISTA: A Panoramic View of Neural Representations

arXiv 2412.02412 ↗First posted 3 Dec 2024cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present VISTA (Visualization of Internal States and Their Associations), a novel pipeline for visually exploring and interpreting neural network representations. VISTA addresses the challenge of analyzing vast multidimensional spaces in modern machine learning models by mapping representations into a semantic 2D space. The resulting collages visually reveal patterns and relationships within internal representations. We demonstrate VISTA's utility by applying it to sparse autoencoder latents uncovering new properties and interpretations. We review the VISTA methodology, present findings from our case study ( https://got.drib.net/latents/ ), and discuss implications for neural network interpretability across various domains of machine learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 11 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

6 of 11 references.

References · 6

  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  2. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  3. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  4. 2024Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2cited by 394
  5. 2024The Platonic Representation Hypothesiscited by 382
  6. 2023Getting aligned on representational alignmentcited by 143

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Addressing divergent representations from causal interventions on neural networks
  2. 2024Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
  3. 2022Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Paper
  4. 2025The Origins of Representation Manifolds in Large Language Models
  5. 2026Bilinear autoencoders find interpretable manifolds
  6. 2026Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
  7. 2026Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders
  8. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probing