# Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

arXiv: https://arxiv.org/abs/2403.05846 · HTML: https://mlsanity.com/paper/2403.05846/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 9 Mar 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://mlsanity.com/paper/2311.04897/) (2023)
- [Jump to Conclusions: Short-Cutting Transformers With Linear Transformations](https://mlsanity.com/paper/2303.09435/) (2023)
- [Generating images of rare concepts using pre-trained diffusion models](https://mlsanity.com/paper/2304.14530/) (2023)
- [The Hidden Language of Diffusion Models](https://mlsanity.com/paper/2306.00966/) (2023)
- [VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers](https://mlsanity.com/paper/2305.13417/) (2023)
- [ReFACT: Updating Text-to-Image Models by Editing the Text Encoder](https://mlsanity.com/paper/2306.00738/) (2023)

## Built on by (most cited first, 30 of 30)

- [Golden Noise for Diffusion Models: A Learning Framework](https://mlsanity.com/paper/2411.09502/) (2024)
- [SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders](https://mlsanity.com/paper/2501.18052/) (2025)
- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2405.14828/) (2024)
- [textitRevelio: Interpreting and leveraging semantic information in diffusion models](https://mlsanity.com/paper/2411.16725/) (2024)
- [PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models](https://mlsanity.com/paper/2501.03544/) (2025)
- [TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation](https://mlsanity.com/paper/2503.07050/) (2025)
- [When Are Concepts Erased From Diffusion Models?](https://mlsanity.com/paper/2505.17013/) (2025)
- [Beyond Transcription: Mechanistic Interpretability in ASR](https://mlsanity.com/paper/2508.15882/) (2025)
- [SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders](https://mlsanity.com/paper/2509.21379/) (2025)
- [Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations](https://mlsanity.com/paper/2501.19066/) (2025)
- [VSC: Visual Search Compositional Text-to-Image Diffusion Model](https://mlsanity.com/paper/2505.01104/) (2025)
- [Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks](https://mlsanity.com/paper/2511.19265/) (2025)
- [NL-Eye: Abductive NLI for Images](https://mlsanity.com/paper/2410.02613/) (2024)
- [Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models](https://mlsanity.com/paper/2504.01137/) (2025)
- [Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation](https://mlsanity.com/paper/2503.09830/) (2025)
- [Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection](https://mlsanity.com/paper/2602.19631/) (2026)
- [Decoding Vision Transformers: the Diffusion Steering Lens](https://mlsanity.com/paper/2504.13763/) (2025)
- [BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation](https://mlsanity.com/paper/2509.13496/) (2025)
- [Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers](https://mlsanity.com/paper/2603.02919/) (2026)
- [When Do Diffusion Models learn to Generate Multiple Objects?](https://mlsanity.com/paper/2605.00273/) (2026)
- [Vision-Language Binding in In-Context Image Generation](https://mlsanity.com/paper/2605.24624/) (2026)
- [Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2605.25941/) (2026)
- [Text-to-Image Models Need Less from Text Encoders Than You Think](https://mlsanity.com/paper/2606.03715/) (2026)
- [A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers](https://mlsanity.com/paper/2606.07593/) (2026)
- [Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment](https://mlsanity.com/paper/2606.30262/) (2026)
- [AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models](https://mlsanity.com/paper/2607.06120/) (2026)
- [Simile Understanding in Text-to-Image Models: An Evaluation Framework](https://mlsanity.com/paper/2608.04750/) (2026)
- [Learning to Read the Contextual Tokens in Diffusion Transformers](https://mlsanity.com/paper/2610.06844/) (2026)

## Abstract (arXiv)

Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. Using the Diffusion Lens, we perform an extensive analysis of two recent T2I models. Exploring compound prompts, we find that complex scenes describing multiple objects are composed progressively and more slowly compared to simple scenes; Exploring knowledge retrieval, we find that representation of uncommon concepts requires further computation compared to common concepts, and that knowledge retrieval is gradual across layers. Overall, our findings provide valuable insights into the text encoder component in T2I pipelines.