- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper extends logit lens readouts from single tokens to multi-token concepts. Concept Lens is training-free: PROPOSE generates candidates from the source prompt, and SCORE ranks them via ridge-projected concept vectors, independently of generation probability. The method is evaluated on a newly constructed multi-hop cloze benchmark across several models, with controls that fix candidates while swapping source states to verify activation-dependent ranking. Calibration costs a fraction of what library-based alternatives require.
Critical strengths
-
The method extends readouts from individual tokens to complete concepts. Complete entities and phrases make intermediate representations easier to interpret than isolated token fragments.
-
It supports concept readout and intervention with little preparation. The method produces both concept labels and representations that can modify model activations, without training an auxiliary model.
Critical weaknesses
-
The main comparisons do not clearly establish where the method’s advantage comes from. The main baseline in Table 2 is Template Lens, whose fixed concept library is missing many target concepts. Better results may therefore come from finding more candidates rather than scoring them more accurately. Even after adding the correct target, the remaining candidates differ between methods. The main text also lacks direct comparisons with methods that generate multi-token descriptions, leaving the claimed faithfulness advantage over generative methods unsupported by direct evidence.
-
The paper’s organization makes the method and evaluation difficult to follow. Figure 1 repeats the Read and J-lens lists but leaves out how candidate vectors are constructed and compared with the source activation. Readers must piece together these steps from the equations. The experimental setup is also scattered: models are introduced in Section 4, while the dataset and evaluation protocol appear in Section 5.1, making the overall setup harder to grasp. Finally, several valuable control experiments in the appendix directly support the paper’s reliability claims and should be included in the main text.
Questions for authors
1.With the same source activations and output budget, is Concept Lens more accurate than existing lightweight generative methods, and does it better reflect changes in the activations?
2.In Table 2’s oracle setting, does Concept Lens retain its advantage over Template Lens when both use identical candidate sets and the same vocabulary competitors?
7 comments
(2/2) [Q1, W1] Generative methods under the same activation and budget: more accurate and activation-faithful
TL;DR:
Thank you for asking for a direct comparison with generative methods; we agree it belongs in the main text. At the same activations and with a matched output budget, Concept Lens is more accurate than Patchscopes and SelfIE on our cleaned benchmark (49.1% Rank@10 with R-lens vs at most 15.8%) and on two of three public benchmarks; SelfIE leads on Hopping Too Late. When the activation changes, our ranking follows it, while Patchscopes often returns the same text for different activations and both generative methods rarely name the injected concept.
1. Accuracy
We compare Concept Lens with Patchscopes (Ghandeharioun et al., 2024) and SelfIE (Chen et al., 2024) at the same activations, following their official implementations and released prompts. Each baseline gets greedy decoding plus 10 samples per layer, one output more than our top 10, and any whole-word mention of the target counts as a hit, which is more lenient than the exact match we require of our own method.
Table 2. Rank@10 (%) on our cleaned benchmark and three public benchmarks. Our target must rank in the top 10 at any layer of the workspace band; for Patchscopes and SelfIE, a whole-word mention in any output at any layer counts as a hit. Averaged over five models on our cleaned benchmark (the 1,031 clozes left after removing those whose answer is a prefix of the concept, following Reviewer yzCg) and over three models on the public benchmarks (1,546 queries, each passing separate bridge-answer and final-answer checks on all three models).
| Method | Ours (cleaned) | TwoHopFact | Hopping Too Late | MQuAKE |
|---|---|---|---|---|
| Template Lens | 26.8 | 9.0 | 7.3 | 19.6 |
| Patchscopes | 14.2 | 5.8 | 15.0 | 8.2 |
| SelfIE | 15.8 | 6.9 | 30.1 | 27.4 |
| Concept Lens (J-lens) | 31.2 | 24.1 | 24.6 | 39.7 |
| Concept Lens (R-lens) | 49.1 | 29.3 | 29.2 | 46.5 |
2. Reflecting activation changes
A reader that reads the activation must change its output when the activation changes, and change it to the right concept. We test this in two ways.
(a) Swap in the partner's activation. We use the counterfactual pairs of App. D.3: two prompts share a relation but require different concepts. With the partner's activation, the readout should move to the partner's concept.
- Concept Lens (candidates and representations fixed): the injected concept ranks in the joint top-10, vocabulary included, in 71.1% of cases (Llama-8B, L27, 204 pairs), 87.0% (Gemma-12B, L43, 131 pairs) and 64.9% (Qwen3-14B, L32, 124 pairs), while the source concept drops to 0.7%, 3.8% and 10.1%.
- Patchscopes and SelfIE, given the same activations at the same layer, name the injected concept in at most 3.8% of greedy outputs (9.3% with samples). Patchscopes returns identical greedy text for the two different activations of a pair in 36.3–41.1% of pairs.
Table 3. Generative readouts after swapping in the partner activation. Percentages for greedy decoding; parentheses: greedy or any of the 10 samples, omitted when equal. Pairs follow: both sides name the concept of their injected activation. Identical greedy text: both sides produce the same greedy string.
| Model | Method | Names injected concept | Names the other concept | Pairs follow | Identical greedy text |
|---|---|---|---|---|---|
| Llama-8B | Patchscopes | 2.7 (7.1) | 0.0 | 0.5 (2.0) | 36.3 |
| Llama-8B | SelfIE | 2.0 (3.7) | 0.0 | 0.0 (0.5) | 0.5 |
| Gemma-12B | Patchscopes | 3.8 (8.4) | 0.0 (0.4) | 1.5 (3.8) | 40.5 |
| Gemma-12B | SelfIE | 0.0 | 0.0 (0.4) | 0.0 | 8.4 |
| Qwen3-14B | Patchscopes | 2.0 (4.8) | 0.0 | 0.0 (0.8) | 41.1 |
| Qwen3-14B | SelfIE | 2.8 (9.3) | 0.0 | 0.0 (1.6) | 4.0 |
(b) Feed an activation that holds no specific concept. We replace each activation with the mean over all prompts of these pairs at the same layer; the readout should at least change. Patchscopes returns exactly the same greedy text on 30.4–47.2% of prompts across five models: its output often comes from its prompt, not from the activation. SelfIE's text usually changes, but as Table 3 shows, it rarely names the right concept. The top-10 of Concept Lens changes on every prompt; a ranked list changes more easily than a single string, so this test mainly exposes Patchscopes.
Follow-up: Revised Manuscript and Method Clarifications
Dear Reviewer pUpR,
We would like to let you know that we have uploaded a substantially revised version of the manuscript, incorporating the changes discussed in our rebuttal.
We have also posted an Official Comment summarizing the major revisions, including the clearer method presentation and additional reliability experiments addressing your concerns.
We would greatly appreciate your feedback on the revised manuscript and would be happy to address any remaining questions.
Best regards, The Authors
(1/2) [Q2, W1, W2] Identical candidates and competitors, and the reorganization
TL;DR:
Thank you for this precise question; it isolates where our advantage comes from. With identical candidates (one shared 39,930-concept bank containing every target) and the same vocabulary competitors, Concept Lens beats Template Lens by 4.6–14.3 points on four models and trails it by 6.4 points on Llama-70B. The advantage therefore does not come only from finding more candidates: on identical candidates, our representations rank the target higher on most models. We also agree with your points on organization and will restructure the paper as described in Section 3.
1. Identical candidates and competitors (Q2)
Both methods rank the same 39,930-concept bank together with the full vocabulary, so every target is available on all 2,400 clozes. Concept Lens does not use its own proposals here, and the scoring rule is shared. So only the concept representations differ: Template Lens uses its template representations, and Concept Lens uses its carrier representations. This setting differs from the oracle-candidate setting in Table 2 of the paper, where each method ranked its own candidates plus the target (Template Lens: its 38,400-concept bank; ours: at most 25 proposals per layer), so the numbers are not comparable to that table.
Table 1. Rank@10 (%) with identical candidates and vocabulary competitors. Best rank across the workspace band.
This test answers your question by isolating the representations, and it helps trace where the advantage comes from. As the main comparison, however, it would be unfair to Concept Lens: it imposes a fixed concept bank, the very limitation of Template Lens, on a method designed to need none. In normal use, Concept Lens proposes its own prompt-specific candidates, so the end-to-end comparison in Table 2 of the paper reflects how the two methods are actually used. Even on Template Lens's terms, Concept Lens leads on four of five models.
2. Where the advantage comes from (W1)
Both stages contribute. On identical candidates, SCORE ranks the target higher on four of five models (Table 1). In ordinary use, PROPOSE also supplies targets that a fixed library lacks: the Template Lens library contains 25.7% of our targets, while PROPOSE covers 30.1–75.5% with at most 25 prompt-specific candidates per layer and no library (Table 2 of the paper). The direct comparison with generative methods is in comment 2/2.
3. Organization (W2)
We agree and will revise as follows: