- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies how token selection affects SAE ablation scores. It compares measurements at each dictionary's preferred positions with measurements at shared positions, then estimates variance components and ranking reliability. Experiments across seven models motivate a reporting standard for position selection and dictionary comparisons.
Critical strengths
-
Figure 1b directly shows substantial variation across positions within a single dictionary. The released-dictionary comparisons in Figure 3 show that even similar decoder directions often select different tokens. These observations support documenting measurement positions.
-
The controlled comparisons use the same retained latents in both measurement designs. The alternative selection rule and fixed-latent analyses in Appendices C and D address useful robustness questions, including cases where the result weakens.
Critical weaknesses
-
The variance analysis is not specified sufficiently to assess the headline reliability gains. Section 3 omits the full moment equations, and the response scale is unclear. Shared positions can induce covariance across arms within a latent. If the estimator treats those observations as independent replicates, subtracting within-cell variance from the interaction mean square can underestimate the interaction, with clipping producing zero estimates. This is a concern about an unspecified estimator, not a demonstrated implementation error. Latent bootstrapping alone does not resolve it. The reported reliability improvement also follows algebraically from the estimated interaction reduction, so it is not independent validation of that reduction.
-
The comparison population limits the proposed standard. Both shared-position rules require every arm to fire and retain only 22% to 50% of sampled latents. Appendix C changes the ranking rule but preserves this conditioning. Greater agreement on this subset does not establish whether excluded differences reflect measurement noise or meaningful differences in feature support. Shared initialization also does not guarantee that corresponding features remain equivalent after training. For released dictionaries, the paper establishes position disagreement but does not show how shared measurements change a substantive dictionary comparison.
Questions for authors
-
What response transformation and moment equations produce Table 1? Can an analysis that explicitly models shared-position covariance recover the reported gains and agree with directly measured ranking consistency?
-
What target population does the standard aim to measure? Can the existing results show a substantive dictionary comparison that changes under the proposed protocol, with feature correspondence checked after training?