- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper addresses the feature matching problem between sparse autoencoder dictionaries of different layers or models. Based on non-negative activations on shared samples, it constructs a max-min common activation relationship. By leveraging Dowker duality, it establishes the equivalence of the continuous homology on both sides of this relationship. Through bidirectional mutual selection, it obtains partial correspondences with zero round-trip error. It jointly evaluates the matching results using coverage rate and geometric distortion. In terms of validation, the authors conducted synthetic transformation experiments such as permutation, scaling, noise addition, splitting, and merging. In twelve groups of precise permutation tasks with different widths and sparsity configurations, the accuracy of retained matches reached 100% and geometric distortion was zero! Further, using the public dictionaries of GPT-2 and Gemma-2-2B, cross-layer experiments were conducted and compared with methods such as activation correlation and decoder cosine to reveal the sample number saturation phenomenon in the real dictionary and the differences in layer-wise matching coverage as the model and depth change.
Critical strengths
- The method directly utilizes the co-activation relations on the shared samples, without requiring the two dictionaries to have the same width or share the activation coordinate space, nor does it need to retrain the joint dictionary.
- The bidirectional mutual selection allows the method to retain only the feature pairs that mutually support, and present the matching range through coverage.
Critical weaknesses
- There is no main figure, making it difficult to understand the author's intention, and the format is too messy, especially the "Contributions." and its contents are even divided into two pages on page 1.
- Can the Abstract contain a formula?
- I'm not entirely convinced that the experimental results are 100% accurate.
- The round-trip error on the mutually selected set is zero, which is guaranteed by the definition. Even smaller geometric distortion cannot rule out semantic errors, because the corresponding errors in the symmetrical structure may still maintain a distance.
- The 100% accuracy rate emphasized in the paper only appears in the precise permutation experiments. The noisy experiment in Table 1 has dropped to 82.6%, so it cannot be generalized as a universal correctness guarantee.
- On page 2, Eq. 2 can provide an effective upper bound, but the round-trip displacement condition used in the proof is overly restrictive and cannot lead to the conclusion of minimality.
- Theorem 2 mainly represents a direct application of the existing Dowker duality theory. Its conclusion is also valid for unrelated dictionaries, and it cannot be used to prove independently that two dictionaries have similar semantic structures.
Questions for authors
Please see "Critical Weaknesses".
3 comments
To be honest, Figure 1 is not the main figure. It is recommended to refer to the top-level conference papers. I maintain my rating.
Redrawn Figure 1
Thank you for the follow-up. We have redrawn Figure 1 as an overview of the method, on page 2 of the updated PDF. From left to right it shows the two dictionaries evaluated on the same inputs, the three checks applied to every candidate pair, and the output. The checks are the mutual best partners under mean co-activation, the exact certificate that compares the two within-dictionary Vietoris–Rips complexes through the matching (Proposition 3), and the sample-permutation test (Proposition 4). The output is the committed set, with the partner, slack and p-value of each pair. One toy example runs through all panels and the caption follows it: a feature whose partner prefers another feature is not matched, and a mutual pair at chance level is dropped by the test.
We would be grateful to know whether any concern remains on the other points of the review: the exactness of the certificate (Proposition 3, checked in Appendix A and by a script in the supplementary material), precision of 1.000 under every transformation except absorption (0.988) in Table 1, which the supplementary material reproduces from scratch, the symmetric case in which small distortion does not imply correctness (Section 4.1), the intervention tests on GPT-2 (Section 5.1), and the role of Theorem 2. If these points are now resolved, we hope the assessment can reflect them.
We are glad to answer any further questions during the discussion.
response for Reviewer juE1
We thank the reviewer for a careful reading. In particular, the point about the minimality of Eq. 2 was correct, and fixing it gave a stronger result.
Point 1 (main figure and Contributions). Figure 1 (new) shows the pipeline on a toy example: shared samples, the cross relation, the induced maps and the mutual set, the certificate and per-pair slack, and the permutation test that drops a mutual but chance-level pair. The Contributions are now a compact paragraph that does not break across pages.
Point 2 (formula in the abstract). Removed. The abstract is now formula-free.
Point 3 (precision for every transformation). The revision reports precision against ground truth for every transformation instead of a blanket statement, and the revised matcher is exact in all but one of them (Table 1). Precision is 1.000 under permutation, rescaling, noise σ=0.01–0.10, splitting and merging, and 0.988 under absorption. Between unrelated dictionaries, 1.4% of features are committed (9 of 640), within sampling error of the nominal α=1% (binomial tail 0.19). To make this directly verifiable, the supplementary material contains a script that generates benchmark A, runs the matcher and the test over the ten seeds, and prints Table 1 as it appears in the paper, in about two minutes on a CPU.
Point 4 (zero round-trip error, and wrong matches with small distortion). Both points are now explicit in the paper, and §4.1 turns the second into an experiment. On dictionaries whose co-activation geometry has a symmetry (features on a regular grid of the torus), mapping every feature to the partner of its translate is entirely wrong. This map has δmut = 0.173, close to the true correspondence's 0.113, and its mean slack is indistinguishable from the truth's. It is rejected by the shared-sample mutual maximum, not by the geometry: the calibrated matcher recovers the truth with precision 1.000, while Gromov–Wasserstein, which sees only the two geometries, reaches 0.028. The paper now states what each part certifies. The certificate measures geometric consistency, and identity comes from the shared samples, through the mutual rule and the permutation test.
Point 5 (precision under noise). This was the most important experimental point, and it led to two changes in the matcher. Matching is now by mean co-activation (§3.1), because max–min scores tie exactly through saturation and are decided by a single sample, which is what failed under noise. A per-pair permutation test (§3.2) is added, valid at level α for each committed pair (Proposition 4). Together they give precision 1.000 and coverage 1.000 at every noise level from σ=0.01 to 0.10 (Table 1). The submitted rule had precision 0.826 and coverage 0.527 at σ=0.05.
Point 6 (the round-trip term of Eq. 2). The reviewer is right. The round-trip term should have coefficient 1/4 and be taken in pairwise form, 41maxa,a′[d1(a,νμa′)−d1(a,a′)]+. The new Proposition 3 gives the exact least δ, necessary and sufficient, and its proof needs no triangle inequality. That matters here, because the co-activation dissimilarity violates it in 42% of code-derived instances. The formula agrees with a direct search over δ to within 5×10−13 on 700 instances. The old bound was strictly loose in 99.5% of metric instances (Appendix A). On the mutual set both round-trip terms vanish, so δmut and the results that use it are unchanged.
Point 7 (the role of Theorem 2). The revision states the theorem's role precisely (§2). It is the filtered Dowker duality of Chowdhury and Mémoli applied to the cross relation. Its role is well-posedness: the comparison does not depend on which dictionary is the source. The evidence of correspondence comes from the mutual rule and the permutation test, which commit to 1.4% of features between unrelated dictionaries, and from the intervention tests on GPT-2 (§5.1). The paper's own theoretical results are the exact certificate (Proposition 3) and the per-pair validity of the test (Proposition 4).
We are glad to answer any further questions during the discussion.