# Visualizing Spatial Semantics of Dimensionally Reduced Text Embeddings

arXiv: https://arxiv.org/abs/2409.03949 · HTML: https://mlsanity.com/paper/2409.03949/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2024.

## Built on by (most cited first, 2 of 2)

- [LLM-Augmented Semantic Steering of Text Embedding Projection Spaces](https://mlsanity.com/paper/2605.01957/) (2026)
- [Scalable Semantic Steering of Embedding Projections](https://mlsanity.com/paper/2607.03978/) (2026)

## Abstract (arXiv)

Dimension reduction (DR) can transform high-dimensional text embeddings into a 2D visual projection facilitating the exploration of document similarities. However, the projection often lacks connection to the text semantics, due to the opaque nature of text embeddings and non-linear dimension reductions. To address these problems, we propose a gradient-based method for visualizing the spatial semantics of dimensionally reduced text embeddings. This method employs gradients to assess the sensitivity of the projected documents with respect to the underlying words. The method can be applied to existing DR algorithms and text embedding models. Using these gradients, we designed a visualization system that incorporates spatial word clouds into the document projection space to illustrate the impactful text features. We further present three usage scenarios that demonstrate the practical applications of our system to facilitate the discovery and interpretation of underlying semantics in text projections.