# Emergence and Localisation of Semantic Role Circuits in LLMs

arXiv: https://arxiv.org/abs/2511.20910 · HTML: https://mlsanity.com/paper/2511.20910/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 26 of its 64 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 26 of 26)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Transcoders Find Interpretable LLM Feature Circuits](https://mlsanity.com/paper/2406.11944/) (2024)
- [Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms](https://mlsanity.com/paper/2403.17806/) (2024)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [LLM Circuit Analyses Are Consistent Across Training and Scale](https://mlsanity.com/paper/2407.10827/) (2024)
- [Disentangling Syntax and Semantics in the Brain with Deep Networks](https://mlsanity.com/paper/2103.01620/) (2021)
- [Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks](https://mlsanity.com/paper/2406.02550/) (2024)
- [Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference](https://mlsanity.com/paper/2408.08590/) (2024)
- [Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training](https://mlsanity.com/paper/2310.16484/) (2023)
- [Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL](https://mlsanity.com/paper/2405.06410/) (2024)
- [Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models](https://mlsanity.com/paper/2506.18141/) (2025)
- [A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models](https://mlsanity.com/paper/2502.08660/) (2025)
- [CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment](https://mlsanity.com/paper/2502.11066/) (2025)
- [TRACE for Tracking the Emergence of Semantic Representations in Transformers](https://mlsanity.com/paper/2505.17998/) (2025)
- [TRACE: Training and Inference-Time Interpretability Analysis for Language Models](https://mlsanity.com/paper/2507.03668/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach](https://mlsanity.com/paper/2605.21303/) (2026)
- [Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation](https://mlsanity.com/paper/2608.22034/) (2026)

## Abstract (arXiv)

Despite displaying semantic competence, large language models' internal mechanisms that ground abstract semantic structure remain insufficiently characterised. We propose a method integrating role-cross minimal pairs, temporal emergence analysis, and cross-model comparison to study how LLMs implement semantic roles. Our analysis uncovers: (i) highly concentrated circuits (89-94% attribution within 28 nodes); (ii) gradual structural refinement rather than phase transitions, with larger models sometimes bypassing localised circuits; and (iii) moderate cross-scale conservation (24-59% component overlap) alongside high spectral similarity. These findings suggest that LLMs form compact, causally isolated mechanisms for abstract semantic structure, and these mechanisms exhibit partial transfer across scales and architectures.