# EL-VIT: Probing Vision Transformer with Interactive Visualization

arXiv: https://arxiv.org/abs/2401.12666 · HTML: https://mlsanity.com/paper/2401.12666/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Self-Attention Attribution: Interpreting Information Interactions Inside Transformer](https://mlsanity.com/paper/2004.11207/) (2020)
- [Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models](https://mlsanity.com/paper/1804.09299/) (2018)
- [CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization](https://mlsanity.com/paper/2004.15004/) (2020)
- [Towards Better Analysis of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.07043/) (2016)
- [Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models](https://mlsanity.com/paper/2009.07053/) (2020)
- [Understanding Hidden Memories of Recurrent Neural Networks](https://mlsanity.com/paper/1710.10777/) (2017)
- [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://mlsanity.com/paper/1809.01587/) (2018)
- [TensorFlow.js: Machine Learning for the Web and Beyond](https://mlsanity.com/paper/1901.05350/) (2019)
- [Direct-Manipulation Visualization of Deep Networks](https://mlsanity.com/paper/1708.03788/) (2017)
- [Dodrio: Exploring Transformer Models with Interactive Visualization](https://mlsanity.com/paper/2103.14625/) (2021)
- [A Unified Understanding of Deep NLP Models for Text Classification](https://mlsanity.com/paper/2206.09355/) (2022)
- [GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks](https://mlsanity.com/paper/2011.11048/) (2020)
- [Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding](https://mlsanity.com/paper/2106.12839/) (2021)
- [Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?](https://mlsanity.com/paper/2210.07646/) (2022)

## Built on by (most cited first, 3 of 3)

- [VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Models](https://mlsanity.com/paper/2509.14571/) (2025)
- [From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers](https://mlsanity.com/paper/2604.23452/) (2026)
- [ViT-Explainer: An Interactive Walkthrough of the Vision Transformer Pipeline](https://mlsanity.com/paper/2604.02182/) (2026)

## Abstract (arXiv)

Nowadays, Vision Transformer (ViT) is widely utilized in various computer vision tasks, owing to its unique self-attention mechanism. However, the model architecture of ViT is complex and often challenging to comprehend, leading to a steep learning curve. ViT developers and users frequently encounter difficulties in interpreting its inner workings. Therefore, a visualization system is needed to assist ViT users in understanding its functionality. This paper introduces EL-VIT, an interactive visual analytics system designed to probe the Vision Transformer and facilitate a better understanding of its operations. The system consists of four layers of visualization views. The first three layers include model overview, knowledge background graph, and model detail view. These three layers elucidate the operation process of ViT from three perspectives: the overall model architecture, detailed explanation, and mathematical operations, enabling users to understand the underlying principles and the transition process between layers. The fourth interpretation view helps ViT users and experts gain a deeper understanding by calculating the cosine similarity between patches. Our two usage scenarios demonstrate the effectiveness and usability of EL-VIT in helping ViT users understand the working mechanism of ViT.