- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies how Duplicate Token Heads (DTHs), a set of special attention heads, route context information through repeated tokens in the input. The paper assumes that these repeated tokens serve as information anchors: DTHs collect, cache and forward contextual information to the repeated positions later in the text for later retrieval. It first uses a DTH score together with activation patching on natural text to locate DTHs that are genuinely functional, and then analyzes the query–key interactions to explain how these heads perform retrieval across matched and unmatched tokens. Experiments on six models and nine simple tasks from three families show that only a small subset of DTHs actually transfers task-relevant information: their addressing is not based on simple token matching, instead it is modulated by the prefix context through query–key interactions. The longer the context, the more severe the loss caused by ablating functional DTHs. The paper also finds that the sets of DTH sets overlap with each other across tasks, and observes weak compensatory effects in ICL.
Critical strengths
- The experiments cover a fairly diverse set of models and tasks, so the conclusions are reasonably robust.
- The procedure for finding DTHs and functional DTHs is sound, and the DTHs identified on general text such as Wikipedia generalize well. This can help guide follow-up work of the same kind.
Critical weaknesses
- The practical value of the paper is limited. As an interpretability paper, it does explain how DTHs work when the model performs retrieval, but it does not suggest a pratical application for this finding, and all the experiments are built on simple toy tasks.
- The role of DTHs is not separated from plain retrieval. Consider a retrieval setting in which no token is repeated (e.g. the question is paraphrased so that it no longer contains the identical token from the context), DTHs should then no longer be critical to retrieval, yet the paper never discusses this case.
- The writing has several problems: the DTH score in Sec. 2.3 does not give a formal formula; references to figures are inconsistent, as in "Fig." (Line 72) vs. "Figure" (Line 185); Fig. 2 is never referenced anywhere in the text; no Related Work section that discusses how this paper differs from prior work. Since the main text is around 8.5 pages and still has some room, the authors should fill these gaps.
Questions for authors
- A classic retrieval task setting is "Needle in a Haystack", where a sentence is inserted somewhere in a long context and the model must locate it precisely. It tests robustness in long contexts and has clear practical value, so the paper would be much stronger if the authors verified the DTH findings on this setting.
- Why do the DTHs found on static text fail to become functional DTHs in the later activation patching? Is there some parameter-level or behavioral difference that keeps only some DTHs from being genuinely functional?
- Some models in Sec. 2.2 have both base and instruct versions. Would the distribution of DTHs differ between them?
- Taking Fig. 1 as an example, do DTHs pay particular attention from to ? The figure only shows the attention from the answer position to and . Before the Query is actually asked, I am curious whether DTHs already store the relevant information at the repeated token positions in advance.
4 comments
Q3 DTH Distribution for Base and Instruct Versions: We additionally compared the base and instruction-tuned/post-trained versions of Llama-3.1-8B and Qwen3-8B. We find substantial overlap in both the DTH candidates identified on the general-text discovery dataset and the functional-DTHs identified on the entity tracking task. Notably, for both model families, the six heads with the highest recovery are identical across versions and retain the same ranking. These results suggest that post-training largely preserves existing mechanisms, which is consistent with the findings of Prakash et al. (2024).
Table: DTH Overlap Between Base and Post-trained Models
Model family Shared / per-version candidates Candidate Jaccard overlap (%) Shared / per-version functional-DTHs Functional Jaccard overlap (%) Llama-3.1-8B: Base vs. Instruct 49/52 89.09 7/8 77.78 Qwen3-8B: Base vs. Post-trained 55/58 90.16 6/9 50.00
Jaccard overlap is the intersection size divided by the union size.
Q4 Mechanism Generalization: Thank you for this interesting question.
-
First question. Our mechanism predicts that functional-DTHs attend from a₂ to a₁ when their contextual information matches. We verified this using inputs such as: "The apple is in Box A, the orange is in Box B. Put the orange into Box A. Box A contains the". At the second "A", functional-DTHs indeed attend to the first "A". For Qwen3-8B, 7 of the 9 functional-DTHs place their maximum attention on the first "A". For the remaining two heads, the first "A" receives the second- or third-highest attention.
-
Second question. If we understand correctly, you are asking whether a₂ thereby already contains a₁'s information before the query. Attention from a₂ to a₁ implies that some information is written into a₂, but which information is written remains unclear. In a closely related box-tracking setting, Tang et al. (2026) found that information accumulated from earlier occurrences is hardly linearly decodable at later occurrences of the same box ID. Therefore, determining whether a₂ carries a₁'s task-relevant information in another form, and whether this information is used downstream, requires causal analysis, which we leave to future work.
Kindly reminder
Thank you for the response. It seems that the authors forget to update the revised paper? I would appreciate it if the paper is updated timely.
Sorry for late upload. Revised paper has been update.
Thank you for the careful review of our paper. Your suggestions and questions have been very helpful in improving the quality of our work. Below, we respond to each of your points.
W1 Practical Value: Thank you for recognizing our explanation of how DTHs work. We agree that we do not propose a concrete practical application. However, we believe that interpretability research provides a foundation for understanding the capabilities of frontier models, and in this sense it can be viewed as a form of application in its own right. Please see our response to Reviewer kAQx (Q1) for details.
In addition, the use of simple tasks is a deliberate design choice. Activation patching and QK decomposition require counterfactual inputs that differ from the original input only minimally, and such inputs are difficult to construct in open-ended text. This is standard practice in mechanistic interpretability; for example, the IOI study (Wang et al., 2023) adopts the same approach.
W2 Retrieval Without Repeated Tokens: Thank you for this insightful suggestion. Following it, we added a retrieval setting in which” no token is repeated”, and found that the importance of DTHs does not decrease. This is an interesting result, and it may further broaden our understanding of the role functional-DTHs play in the model. Please see our response to Reviewer kAQx (Q1) for details!
W3 Presentation: Thank you for these helpful comments. We added a a formal formula of the DTH score in Sec. 2.3, unified all figure references, and now reference Fig. 2 in the main text. Regarding the Related Work section: after adding the content requested by the reviewers, the main text no longer has room for a standalone section. We will therefore clearly discuss related work in the Introduction and background, explain how our paper differs from prior work.
Q1 Needle in a Haystack: We added a “Needle in a Haystack” experiment. The results show that, across different context lengths, ablating DTHs still leads to a drop in accuracy for multiple models, although the size of this drop does not consistently increase with context length. These results indicate that DTHs continue to play an important role in long-context retrieval. The tables below report the relative accuracy change after ablation. Columns correspond to insertion positions within the background: 0% denotes the beginning and 100% the end.
Q2 DTHs and Functional-DTHs: Thank you for this insightful question. The DTH score is computed from attention patterns alone, i.e., it measures where a head attends, whereas activation patching measures what the head moves and whether this information is used downstream. A head can therefore consistently attend to repeated tokens without being functional.
Regarding parameter-level differences, we decomposed the OV matrices of these heads but did not find features that clearly separate functional DTHs from other DTHs. Regarding behavioral differences, we found that ordinary DTHs address repeated tokens based on token identity alone: they prefer any occurrence with the same identity, even when its preceding context does not match. In contrast, functional-DTHs appear to select occurrences based on both token identity and contextual information, so their preference for an occurrence with the same identity but mismatched context is substantially weaker (based on findings of section3 ).