- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies whether language models use a geometrically structured representation of the night sky when answering proximity questions. It analyzes residual-stream activations for 188 astronomical objects and 25 prompt templates across seven models. Celestial coordinates are linearly decodable in six models, with reported leave-one-object-out R² values of 73–91% and median angular errors of approximately 11°–18°. The authors fit first- and second-order spherical harmonics, ablate the resulting subspaces, and replace fitted representations to steer responses toward another constellation. They also compare spherical geometry with flat, cylindrical, graph-based, and corpus-derived alternatives, arguing for an irreducible spherical feature manifold.
Critical strengths
-
The representation finding is supported across multiple models and objects. Six of seven models show substantial coordinate decodability, supported by object-level validation and additional 80/20 splits with permutation tests. The paper also reports the weaker gpt-oss result and the reduced prominence under generic prompts. These observations make the finding informative within its stated proximity-task setting.
-
The interventions provide evidence that the fitted spatial subspace is behaviorally relevant. Ablating the eight-dimensional harmonic subspace markedly degrades proximity judgments, while ablating its equal-dimensional complement has little effect. Steering toward another constellation shifts responses toward that target, and writing back the original constellation provides a useful control. Together with the usable-response analysis for ablation, this supports a functional role for the identified information, even though the precise geometric mechanism requires further controls.
Critical weaknesses
-
The exclusion of competing geometries is stronger than the analysis supports. Appendix F.1 regresses the activation squared-distance matrix on squared differences of individual candidate coordinates. For a general linear embedding h = Aφ, the corresponding distance is ΔφᵀAᵀAΔφ, which includes cross terms unless the induced metric is diagonal. Equation (3) therefore does not cover arbitrary linear mixtures of the candidate features. Moreover, with strongly correlated predictors, nonpositive coefficients cannot establish that a representation is absent. The paper acknowledges coefficient instability but nevertheless concludes “complete absence” in F.1 and claims high-confidence exclusion of reducible representations in the abstract. These conclusions should be narrowed to the tested models and metric assumptions, or supported by held-out comparisons that allow suitably regularized candidate metrics and report uncertainty. This matters for the claimed irreducibility, although it does not invalidate the separate decoding and intervention results.
There is also a mathematical ambiguity in the co-occurrence comparison. F.3 equates M* = ΦΛΦᵀ with (ΦΣ)(ΦΣ)ᵀ for Σ = √|Λ|. The latter is Φ|Λ*|Φᵀ and differs from M* if negative eigenvalues are present. A signed or separate input/context factorization may be intended; the paper should clarify the construction and whether the Q_text comparison is affected.
-
The validation and intervention controls limit the strength of the generalization and geometric-specificity claims. Appendix D fits PCA using all objects before holding objects out of the coordinate regression; the accompanying repository protocol explicitly describes this as evaluation conditional on a globally fitted basis. Table 5 does not explain how its reported layers were selected. Appendix C also describes selecting proximity-focused prompts based on performance. The resulting validation is useful for describing the observed representations, but does not fully isolate generalization to objects and prompts that played no role in constructing or selecting the analysis. PCA does not use held-out coordinate labels, so this should not be interpreted as demonstrated label leakage.
The intervention controls also leave unresolved alternatives. The complementary-subspace ablation matches dimension but is not reported to match removed activation variance; E.1 itself acknowledges dimensionality and overlap as potential explanations for the larger effect of second-order components. Steering holds out two templates while retaining the constellation identities in the fitted dataset, and directly naming target B counts as success, although Figure 7 indicates such answers are a minority. The repository specifies 88 source constellations and two templates, giving 176 prompts per arm, and documents object-cluster bootstrap intervals for ablation. The corresponding intervals and paired steering uncertainty should accompany the paper’s reported effects. These limitations weaken claims about a specific spherical computation and its generalization; they do not erase the observed behavioral effects.
Questions for authors
The following questions concern the strength and interpretation of the submitted evidence and could materially affect the assessment.
-
Alternative geometries: Does the spherical advantage persist when each candidate receives a regularized linear map or positive-semidefinite metric, including cross terms, fitted on training objects and evaluated on held-out objects? What uncertainty and sensitivity to coordinate choices support the exclusion claim in F.1?
-
Validation pipeline: How was the layer in Table 5 selected? What results remain when PCA, layer choice, and dimensionality are determined using training objects only, and prompts are specified independently of performance-based selection? Please include variability across the reported object splits.
-
Intervention specificity and statistics: The repository describes 176 prompts per steering arm and object-cluster bootstrap intervals for ablation. Please include the corresponding intervals in the paper and report paired steering uncertainty and usable-response denominators. Does the effect persist with dimension- and variance-matched ablation controls and with source/target identities excluded from fitting? What is the steering success rate when direct answers of B are excluded?
-
Co-occurrence factorization: Is M* in F.3 positive semidefinite in the experiments? If not, what signed or input/context factorization is intended, what was implemented, and does correcting the stated identity change the Q_text comparison?
4 comments
Update: we added a variance-matched-controls version of the ablation experiment. The trends stay the same: controls barely move the performance (they even increase parsed fraction for unknown reasons), l=1 and l=2 on their own harm, but not too much, together they bring accuracy close to chance.
Please see whether this, and the prior changes address your concerns and change your assessment. Given that your review brought up the most of the issues we address in the revision, that your rating was the most harsh, and that you indicated that addressing these issues might change it, we would really appreciate you posting your opinion on the revised paper.
Official Comment by Reviewer GEW9
Thank you for the detailed responses and revisions. The authors have addressed several of my concerns, and I have decided to raise my rating to Weak Reject. I have two remaining concerns:
-
The paper uses only 8 pages despite the 9-page limit. Could the authors clarify whether the current presentation sufficiently develops the methodological contributions and experimental analysis?
-
The manuscript contains noticeable formatting issues, such as single words appearing on separate lines (e.g., Lines 38 and 145), which affect readability. I encourage the authors to improve the typesetting in the revision.
Thank you for reading the revision and for raising your score. We have uploaded a new version that addresses both points.
- Length and development of the methodology. We agree that the main text was too compressed: several of the controls you asked for in your first review appeared only in the appendix. The additions are:
Section 3.3: a formal statement of the harmonic fit and of the ablation and steering interventions (Equation 1). Section 3.3: the variance-matched ablation controls with 95% confidence intervals (Figure 6), together with the variance removed by the dimension-matched control. Section 3.3: per-model steering rates with paired bootstrap intervals and usable-response denominators, including rates with direct answers of B excluded (Table 1). Section 3.3: the variance explained by the l=1 and l=1,2 fits, which shows the bend without any intervention. Section 3.2: the check on 25 new prompt templates that were fixed before any activations were extracted. Section 3.4: the held-out unique-R² protocol for the alternative geometries, including the cylinder axes and chart cuts tested. Section 5: a new Limitations section.
All of this material was already in the appendix or in our earlier replies. It has been moved or restated in the main text, and no claims were changed.
- Typesetting. We fixed the single-word lines at Lines 38 and 145, removed the other single-word line endings in the main text, rescaled the corpus table in Appendix F.3 that extended into the margin, and corrected the remaining typos.
The points in your original review (alternative geometries, validation pipeline, intervention controls, co-occurrence factorization) are not among your remaining concerns. If any technical issues still keep the paper below the acceptance threshold, we would be grateful to know and will address it in the time remaining.
Thank you for the detailed critique, we've tried to address main points of contention as follows.