@article{decomposingandinterpretingimage, title = {Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP}, author = {Sriram Balasubramanian and Samyadeep Basu and Soheil Feizi}, year = {2024}, eprint = {2406.01583}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.01583v2}, }