Explaining How Visual, Textual and Multimodal Encoders Share Concepts
Preprint
Abstract
Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have been restricted to models within the same modality. We propose a novel indicator allowing quantitative comparison of models across SAE features, and use it to conduct a comparative study of visual, textual and multimodal encoders. We also propose to quantify the Comparative Sharedness of individual features between different classes of models. With these two new tools, we conduct several studies on 21 encoders of the three types, with two significantly different sizes, and considering generalist and domain specific datasets. The results allow to revisit previous studies at the light of encoders trained in a multimodal context and to quantify to which extent all these models share some representations or features. They also suggest that visual features that are specific to VLMs among vision encoders are shared with text encoders, highlighting the impact of text pretraining. The code is available at https://github.com/CEA-LIST/SAEshareConceptsKeywords
All Related Versions
This publication has 8 references indexed in Scilit:
- MambaVision: A Hybrid Mamba-Transformer Vision Backbone2025
- Similarity of Neural Network Models: A Survey of Functional and Representational MeasuresACM Computing Surveys, 2025
- Do Vision and Language Models Share Concepts? A Vector Space Alignment StudyTransactions of the Association for Computational Linguistics, 2024
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 22024
- Finding Skill Neurons in Pre-trained Transformer-based Language Models2022
- Array programming with NumPyNature, 2020
- Understanding the role of individual units in a deep neural networkProceedings of the National Academy of Sciences of the United States of America, 2020
- Frequency Distribution of the Values of the Correlation Coefficient in Samples from an Indefinitely Large PopulationBiometrika, 1915