- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies sparse autoencoders as tools for extracting browsable visual concepts from foundation-model patch representations. It evaluates concept rediscovery on ADE20K and FishVista, compares decomposition methods and SAE variants, and ranks features separating Heliconius mimic pairs using a Mann-Whitney-based selectivity score. Expert interpretation links highly ranked butterfly features to known diagnostic traits. The paper explicitly frames these results as preparation for future discovery rather than a new biological discovery.
Critical strengths
- The evaluation measures a property that reconstruction alone cannot guarantee. A representation can reconstruct inputs accurately while spreading a semantic concept across many coordinates. Since the intended use is expert inspection of individual features, axis-aligned probes and concept coverage are appropriate measures of utility. The improvements over PCA and SemiNMF on ADE20K, together with FishVista anatomy recovery, support the value of sparse feature extraction for this purpose.
- The biological case study demonstrates a concrete human-in-the-loop use. The ranking heuristic reduces a large dictionary to a manageable set of candidates, and the displayed activations can be checked against known diagnostic traits. The authors appropriately distinguish this rediscovery result from establishing novel biological knowledge. This bounded empirical contribution is sufficient to be useful without requiring a new SAE architecture.
Critical weaknesses
- Label-free feature learning is not the same as label-free workflow selection. SAE parameters are learned without concept annotations, but layer and SAE choices use labeled probe performance in the rediscovery experiments. In an unannotated discovery setting, that selection signal is unavailable. Furthermore, selecting the best axis from 16,384 latents gives a different search opportunity from a smaller decomposition, so the results combine semantic organization with dictionary-size effects. The central practical question is whether an annotation-independent selection rule retains the reported utility. A fixed transferred configuration or a declared reconstruction/sparsity-based rule would address this directly.
- Species separability does not uniquely identify biological novelty or useful trait diversity. The selectivity score rewards any feature correlated with the species label, including acquisition cues, and does not distinguish a new trait from several redundant encodings of one known trait. Appendix I illustrates this distinction: several top features correspond to the same diagnostic pattern. Expert validation is therefore essential, but feature-level hit rate alone does not measure the number of distinct useful hypotheses produced. Object-only ranking controls and counting distinct validated traits would align the evaluation more closely with the intended discovery task.
Questions for authors
- Clarification: Which layer and SAE selection decisions require concept labels, and which rule would you use unchanged on a dataset without such labels? Can the existing experiments show how a fixed or annotation-independent choice compares with probe-selected configurations?
- Evidence affecting the recommendation: At a comparable dictionary or candidate-inspection budget, does the advantage over the strongest decomposition baseline persist? This would clarify whether improved browsability comes from the representation itself or primarily from a larger candidate pool.
- Evidence affecting the recommendation: Do the top butterfly features remain associated with the diagnostic wing regions when backgrounds and collection labels are excluded? How many distinct diagnostic traits are represented among the top five features for each pair? These checks would sharpen the biological interpretation without requiring a prospective discovery study.
We thank the reviewers for taking the time to give their thoughtful and thorough comments and questions. Our responses to the listed weaknesses and questions are provided below:
The reviewer notes that concept labels were used to select the best SAE for comparison with baseline methods, and that a dimensionality mismatch favors SAEs over baseline methods.
We have updated Table 1 to instead use a label-free selection criterion for which SAE to use for comparison, reporting metrics for the Pareto-optimal SAE with L0 closest to 256 (Similar L0 to PCA/SemiNMF). We aim to compare SAEs to baseline methods at similar levels of sparsity, as we argue that the scalable, overcomplete nature of SAEs is what makes them ideal for trait discovery. The results of this experiment remain the same, with SAEs improving on downstream metrics.
The reviewer notes that background features may have high selectivity scores, and that the same trait may have several highly-ranked, redundant features.
We believe this is an important limitation of this result, and as such, have updated the discussion section to touch on this point. Additionally, we have added details about the number of distinct traits identified in the top-5 selectivity features for each subspecies mimic pair (Section 4.3). Despite this, we believe that concept-label-free hypothesis generation (even when a trait is surfaced multiple times) enables visual feature discovery at scale, allowing domain scientists to quickly identify meaningful and possibly novel traits. Additionally, while background features may drive selectivity, we identify several non-background features based on selectivity ranking.
Q1 Concept labels are used to select which layer of activations to use for evaluation across all methods, comparing SAE variants and model backbones, qualitative examples of features from ADE20K, and measuring the recoverability of specific traits on FishVista. Fine-grained concept labels are not used on Heliconius images.
Q2 When compared to baseline methods, SAEs improve on the percentage of highly-ranked features that correspond to known diagnostic traits at comparable dictionary size (k-means) and candidate inspection budget (k-means/PCA), as detailed in Section 4.3. Furthermore, SAEs improve substantially on quantitative metrics on controlled rediscovery tasks, indicating that SAEs capture features that more holistically capture visual traits (Table 1).
Q3 While we have tested removing backgrounds from images with this approach (with similar results), this is not included as part of this work. Instead, this work is focused on providing a methodology for identifying potentially meaningful visual traits without relying on fine-grained concept labels. We hope to expand on this work in the future by utilizing background removal, and have made note of this in the provided work (Appendix A).