- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies the interpretability of contrastive vision-language models (VLMs) using sparse autoencoders (SAEs). The authors identify the split-dictionary phenomenon, where a shared SAE tends to learn modality-specific features rather than discovering shared cross-modal features. They argue that enforcing a single shared SAE can compromise reconstruction quality, interpretability, and zero-shot performance. To address this issue, they propose a dual-SAE architecture that uses separate SAEs for each modality while retaining co-activation guidance to facilitate cross-modal feature alignment.
Critical strengths
- The authors analyze the activation properties of shared and independent SAEs.
- The authors introduce a permutation matrix to encourage SAEs from different modalities to learn similar concepts.
- The authors conduct experiments on multiple CLIP-style models, such as CLIP and SigLIP.
Critical weaknesses
- The authors only consider conventional shared SAEs, which use a shared encoder and decoder. They overlook an important prior work, VL-SAE [1], which uses a modality-shared encoder to construct concepts and independent decoders to learn modality-specific information. This work appears to have already addressed the problem raised by the authors.
- Although the authors use a permutation matrix to improve concept alignment across modalities, they lack a corresponding evaluation of cross-modal concept consistency. For example, they could measure the CLIP similarity between images and text associated with the same activated concept, as done in VL-SAE.
- As shown in Figure 7, the proposed method still sacrifices model performance for interpretability, unlike works such as VL-SAE and TORINO [2], which improve model performance alongside interpretability.
- The proposed method relies heavily on CLIP's dual-tower alignment architecture and therefore cannot be directly applied to MLLMs like LLaVA and Qwen-VL, which are more capable vision-language models.
[1] Shen, S., Sun, J., Huang, Q., & Wang, S. (2026). Vl-sae: Interpreting and enhancing vision-language alignment with a unified concept set. Advances in Neural Information Processing Systems, 38, 45235-45265.
[2] Renzulli, R., Spadaro, G., Gowda, S., Mazouz, A. E., & Nguyen, V. T. (2026). TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models. arXiv preprint arXiv:2607.04593.
Questions for authors
Overall, I encourage the authors to conduct a more thorough review of existing studies on multimodal SAEs to better clarify the novelty of the problem they aim to address. From my perspective, some of the challenges discussed in this paper appear to have been addressed by prior work (e.g., VL-SAE), which also reports promising results. It would therefore be helpful to include more comprehensive comparisons with these methods to better demonstrate the advantages of the proposed approach and provide further insights into the differences in their performance.
4 comments
W2) Although the authors use a permutation matrix to improve concept alignment across modalities, they lack a corresponding evaluation of cross-modal concept consistency. For example, they could measure the CLIP similarity between images and text associated with the same activated concept, as done in VL-SAE.
The paper already includes experiments for assessing the cross-modal concept consistency. The multimodal monosemanticity score (introduced in [3] and detailed in Section 3.1 and Appendix D) specifically assesses if each neuron is activated for a single cross-modal concept:
- How it works: It is computed by collecting all image and text examples that activate a given neuron, measuring the pairwise similarity between these examples using an external model (CLIP), and weighting each similarity by the corresponding code activation strength.
- What it proves: Because this score is maximized only when activations correspond to image-text pairs with high CLIP similarity, it directly quantifies cross-modal semantic consistency, going beyond top- samples (as done in VL-SAE) to evaluate the entire activating distribution.
As shown in Figures 6, 13, 22, and 26, i-SAEs with Hungarian Matching consistently outperform s-SAEs on this metric, confirming stronger cross-modal concept alignment.
W3) As shown in Figure 7, the proposed method still sacrifices model performance for interpretability, unlike works such as VL-SAE and TORINO, which improve model performance alongside interpretability.
As noted in (W1, Q1) regarding VL-SAE, their approach aggregates SAE outputs with the original dense activations (see Equations. 10 and 11 in [7]). While this effectively boosts task accuracy, it bypasses the SAE bottleneck, allowing the model to still rely on un-decomposed dense features. Similarly, TORINO [8] addresses the different problem of decreasing the number of visual tokens in input to VLMs, thus increasing their efficiency while minimizing performance loss.
In contrast, to rigorously test the faithfulness of the learned concepts, we enforce a strict information bottleneck where contrastive VLM predictions are computed entirely from the reconstructed SAE features. Under pure sparse compression, an accuracy trade-off relative to the uncompressed model is expected.
Crucially, Equation 6 (Section 3.1) factorizes exactly why preserving accuracy under this strict bottleneck is challenging. Each cosine similarity prediction factorizes into a cross-modal co-activation and alignment term, divided by intra-modal interference. To achieve good downstream performance without any shortcut, the SAE decompositions must satisfy three strict geometric conditions:
- Both modalities must preserve fine-grained features within their top- sparse selections;
- Textual and visual top- selections must remain perfectly aligned (losing an important feature in either modality degrades the final logits);
- Intra-modal interference must be minimized to prevent logit distortion.
Viewed through this lens, Figure 7 demonstrates that Independent SAEs retain substantially better downstream performance than Shared SAEs under a true white-box bottleneck. They achieve this precisely because respecting the modality gap better satisfies these three geometric constraints.
W4) The proposed method relies heavily on CLIP's dual-tower alignment architecture and therefore cannot be directly applied to MLLMs like LLaVA and Qwen-VL, which are more capable vision-language models.
The paper specifically tackles the problem of the split-dictionary phenomenon observed in contrastive VLMs output spaces and proposes a solution which exploits the geometry of those spaces by highlighting the limitations of current ones. We acknowledge that expanding the results to multimodal LLMs is a promising research direction, but it is an entirely different scope from what we consider in this work, and we leave it for future developments. Additionally, we stress that contrastive VLMs are still extensively used as the primary visual encoders or text-image alignment modules for multiple applications, including image generation [4], composed retrieval [5], image captioning [6]. Therefore, solving the interpretability challenges specific to dual-tower architectures is a critical contribution in its own right. We believe our findings will directly benefit the interpretability, safety, and reliability of the downstream applications that continue to rely heavily on contrastive VLM backbones.
References
[1] Hyeon-Woo, N., Ye-Bin, M., Lim, S., Byung-Ki, K., & Oh, T. H. Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language. In Forty-third International Conference on Machine Learning, 2026.
[2] Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, and Zeynep Akata. Sparse autoencoders learn monosemantic features in vision-language models. In The Thirty- ninth Annual Conference on Neural Information Processing Systems, 2025.
[3] Chiraag Kaushik, Davis Barch, and Andrea Fanelli. Decomposing multimodal embedding spaces with group-sparse autoencoders. In The Fourteenth International Conference on Learning Representations, 2026.
[4] Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022.
[5] Bill Psomas, George Retsinas, Nikos Efthymiadis, Panagiotis Filntisis, Yannis Avrithis, Petros Maragos, Ondrej Chum, and Giorgos Tolias. Instance-level composed image retrieval. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025.
[6] Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, and Rohit Girdhar. LLMs can see and hear without any training. In Forty-second International Conference on Machine Learning, 2025.
[7] Shen, S., Sun, J., Huang, Q., & Wang, S. (2026). Vl-sae: Interpreting and enhancing vision-language alignment with a unified concept set. Advances in Neural Information Processing Systems, 38, 45235-45265.
[8] Renzulli, R., Spadaro, G., Gowda, S., Mazouz, A. E., & Nguyen, V. T. (2026). TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models. arXiv preprint arXiv:2607.04593.
Thank you to the authors for their response. First, I encourage the authors to incorporate the rebuttal clarifications and promised improvements into the revised manuscript. One advantage of the ICLR review process is that authors can update their submissions, allowing all reviewers to assess the actual improvements to the paper. Second, I understand that the author focus on metrics like faithfulness rather than the performance improvement in downstream tasks. However, it is also necessary to conduct experimental comparisons between the proposed method and existing methods in the indicators that the author focused on.
Rebuttal
Regarding the second strength, we would like to clarify that the permutation matrix is not used to encourage SAEs from different modalities to learn similar concepts. The permutation matrix is used once after training to align the already-learned per-modality dictionaries. As the results about the multimodal monosemanticity score show (Figures 6, 13, 22, 26), independent SAEs are able to learn shared semantics without using any inductive factor during training. This property is emergent.
We thank the reviewer for bringing VL-SAE [7] to our attention. We agree it is an important prior work, and we will certainly include it in the related works section. However, our work is fundamentally different in both goals and scope.
Rather than proposing a new hybrid architecture to maximize downstream task accuracy (as VL-SAE does), our work asks a foundational mechanistic question: "can dense representations of contrastive VLMs be decomposed with a single shared SAE to effectively provide high interpretability while also retaining a faithful representation of the underlying model’s workings, even for modality-specific embeddings?"
By systematically contrasting shared architectures against independent, per-modality SAEs, we demonstrate why explicitly decoupling modalities is essential for faithful interpretability. The key differences that highlight the novelty of our problem setting are:
Taken together, our geometric analysis, faithfulness evaluations, and high-sparsity interpretability benchmarks offer complementary insights to VL-SAE's downstream-oriented framework, addressing essential questions for multimodal interpretability.