- Rating
- 3(+1)
- Confidence
- 2(−1)
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
S²-SAE is an adaptive sparse autoencoder motivated by a spike-and-slab prior. Its encoder combines a learned shared threshold with dual updates controlling average activity; an optional refinement selects a reconstruction-dependent feature budget. Experiments assess reconstruction, feature allocation, behavior preservation and inference cost on two vision datasets and Pythia/Gemma activations. Exact MAP reasoning is restricted to the stated idealized setting; the practical overcomplete encoder is an approximation (pp. 3–5; Appendix A, pp. 13–14).
Critical strengths
-
The vision evaluation spans two datasets and three SAE seeds, with favorable reconstruction results at nearby measured activity levels (p. 6, Figure 1; p. 16, Figure 6; p. 18, Appendix D). Fast inference already obtains these benefits, making the empirical contribution independent of expensive refinement.
-
The probabilistic formulation coherently motivates a shared activation criterion, with the exact-MAP assumptions and practical approximation explicitly separated (p. 4; pp. 13–14, Appendix A). This supplies a principled design rationale and a useful connection between activation costs and average-budget control.
Critical weaknesses
-
The methodological increment is limited and incompletely attributed. Input-dependent activity is already available in JumpReLU and BatchTopK (pp. 2–3). The shared threshold follows from a common activation cost in the chosen prior (pp. 13–14); this is a coherent modeling choice, but its empirical advantage remains to be established. Complete-system comparisons do not isolate threshold sharing from budget control or other training choices, leaving the distinctive design's importance uncertain.
-
Evidence beyond vision remains mixed. In the language experiments, several fast-inference gains are small or negative, and the largest high-ℓ0 Pythia gain is interpolation-sensitive (pp. 6–7; p. 17, Tables 3–4). In Figure 4, four low-to-mid-budget Pythia points lie below the connected baseline frontier; these are not precisely budget-matched comparisons. The text gives refined loss recovery of 0.9285 versus 0.9356 at the lowest-budget example despite favorable MSE (p. 8). Thus behavioral benefits are limited. Additionally, the printed Gemma MSE values are compatible with bf16 rounding; Table 4's +0.38% gain corresponds to about 0.9 bf16 ULP. Actual metric precision is unspecified, so this is a clarification need, not established numerical error (pp. 17–18). These limitations leave robust practical benefits concentrated in vision reconstruction.; several fast-inference gains are small or negative, and the largest high-ℓ0 Pythia gain is interpolation-sensitive (pp. 6–7; p. 17, Tables 3–4). In Figure 4, four low-to-mid-budget Pythia points lie below the connected baseline frontier; these are not precisely budget-matched comparisons. The text gives refined loss recovery of 0.9285 versus 0.9356 at the lowest-budget example despite favorable MSE (p. 8). Thus behavioral benefits are limited. Additionally, the printed Gemma MSE values are compatible with bf16 rounding; Table 4's +0.38% gain corresponds to about 0.9 bf16 ULP. Actual metric precision is unspecified, so this is a clarification need, not established numerical error (pp. 17–18). These limitations leave robust practical benefits concentrated in vision reconstruction.
Questions for authors
-
Which existing result most directly identifies the benefit of threshold sharing separately from average-budget control? An available representative control or a precise account of the combination's distinct contribution would help assess significance.
-
What precision is used to accumulate and report Gemma MSE? With existing checkpoints, can you establish whether the +0.38% comparison is stable to metric precision, and identify language advantages supported by observed points and Figure 4 rather than interpolation alone?
2 comments
Addressing W2, Q1, Q2.
W2/Q2: Gemma-2B benchmark precision (bf16).
To preserve comparability, we matched the published SAE Bench settings. Gemma uses BF16, a 16-bit format used to reduce memory during inference. The SAE Bench evaluator we used carries this limited precision into the MSE calculation and final reported score. The gain in Table 4 corresponds to a gap of 0.00353 MSE, smaller than the spacing of 0.00391 between adjacent BF16 values in that range. Allowing for final rounding alone, the ordering can change, so we treat this comparison as a near tie. In Table 11, even if -SAE and JumpReLU swap ranks at target 280, -SAE still has the best Gemma AvgRank (1.33 vs. 2.00). Pythia uses FP32 and is unaffected by the issue. We decided to report this aspect in the paper to make other researchers aware of the issue in SAEBench evaluation; it is found in a dedicated paragraph in the Appendix C. A separate discussion on the AvgRank-based report is present in Appendix G.2.
W2: These are not precisely budget-matches comparisons.
Those mismatched points correspond to the PAnneal and GatedSAE models, which are more evident in the added Appendix G.1; we do not have access to these model weights and we cannot provide more exact reports over the baseline behavior.
Q1: Which existing result most directly identifies the benefit of threshold sharing separately from average-budget control? A representative control or a precise account of the combination distinct contribution would help assess significance.
We provide an additional ablation study which isolates the benefit of shared thresholding and training procedure. We confirm that the shared threshold has a tangible benefit, while average-budget control is more of a convenience choice. This answer summarizes the extended, common answer reported above ("Ablation study").
Can you identify language advantages supported by observed points and Figure 4 rather than interpolation alone?
In addition to the (interpolation-less) Pareto-based visualizations in Fig. 2, which highlight that our models always belong to the Pareto frontier, Appendix G.1 shows MSE and cosine similarity for each baseline separately. On Gemma at target 72, fast -SAE has MSE 1.60156 and cosine similarity 0.92188 at measured , versus MSE 1.63281 and cosine similarity 0.91797 at for JumpReLU. At the highest Pythia target, fast inference gives MSE 0.000256 at , versus 0.001399 at for the nearby JumpReLU checkpoint. This shows a sizable difference already in the observed scores at nearby sparsities.
Addressing W1, W2, Q1.
The most direct comparison is C1 vs. C3 in the added Tab. 9. Both use the same dual controller and training setup, and they differ only in whether the threshold is shared. We also compare C2 vs. C4 with fixed λ. Sharing the threshold reduces MSE in all six CUB comparisons and all four Pythia comparisons. The three Pythia seeds per cell at target 140 support the C1 vs. C3 ordering in this smaller ablation.
Shared vs. per-feature thresholds with budget control held fixed.
MSE is compared at matched ℓ₀ (lower is better). MSE reduction is 100 × (per-feature MSE − shared MSE) / per-feature MSE within each budget-control setting.
In SAE-based works for language models, gains have notably been small so far (e.g., BatchTopK, JumpReLU). Despite the difficult task, our Pareto-based visualizations in Fig. 2 (where all the S^2 models lie in the Pareto frontier, regardless of interpolation) were complemented with added reports in Appendix G of sensible improvements in other key metrics, including the following AvgRank metric.
The published SAEBench benchmarks follow the same single-seed setting, so we chose to follow the same procedure to ensure fair comparability and to reserve computation power to provide more model training at different sparsity levels. To reassure the reviewer about the impact of this procedure, in the new 30M-token Pythia ablation study at target ℓ0=140, we ran three seeds each for C1 and C3, finding small interseed variability: the MSE standard deviation is at most 1.3×10−4, and all three shared-threshold runs have lower MSE than all three per-feature-threshold runs.
We provide an AvgRank-based analysis (Appendix G.2, reported above) which confirms that fast-inference presents the best average ranking across all baselines considered.