# Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models

arXiv: https://arxiv.org/abs/2311.04131 · HTML: https://mlsanity.com/paper/2311.04131/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 7 Nov 2023.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [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)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark](https://mlsanity.com/paper/2305.17553/) (2023)
- [X-Risk Analysis for AI Research](https://mlsanity.com/paper/2206.05862/) (2022)
- [The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python](https://mlsanity.com/paper/2305.15507/) (2023)
- [Neuron to Graph: Interpreting Language Model Neurons at Scale](https://mlsanity.com/paper/2305.19911/) (2023)
- [System III: Learning with Domain Knowledge for Safety Constraints](https://mlsanity.com/paper/2304.11593/) (2023)

## Built on by (most cited first, 15 of 15)

- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks](https://mlsanity.com/paper/2511.19265/) (2025)
- [Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems](https://mlsanity.com/paper/2408.15550/) (2024)
- [Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer](https://mlsanity.com/paper/2604.24302/) (2026)
- [Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations](https://mlsanity.com/paper/2510.17256/) (2025)
- [Weight Patching: Toward Source-Level Mechanistic Localization in LLMs](https://mlsanity.com/paper/2604.13694/) (2026)
- [How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits](https://mlsanity.com/paper/2605.08348/) (2026)
- [Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge](https://mlsanity.com/paper/2605.16023/) (2026)
- [Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation](https://mlsanity.com/paper/2505.10822/) (2025)
- [An Exploratory Framework for Future SETI Applications: Detecting Generative Reactivity via Language Models](https://mlsanity.com/paper/2506.02730/) (2025)
- [Query Circuits: Explaining How Language Models Answer User Prompts](https://mlsanity.com/paper/2509.24808/) (2025)
- [Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models](https://mlsanity.com/paper/2602.03506/) (2026)
- [Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings](https://mlsanity.com/paper/2604.08192/) (2026)
- [Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs](https://mlsanity.com/paper/2604.16054/) (2026)
- [Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B](https://mlsanity.com/paper/2608.18419/) (2026)

## Abstract (arXiv)

While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called circuits that implement algorithmic functions. We extend this research by analyzing and comparing circuits for similar sequence continuation tasks, which include increasing sequences of Arabic numerals, number words, and months. By applying circuit interpretability analysis, we identify a key sub-circuit in both GPT-2 Small and Llama-2-7B responsible for detecting sequence members and for predicting the next member in a sequence. Our analysis reveals that semantically related sequences rely on shared circuit subgraphs with analogous roles. Additionally, we show that this sub-circuit has effects on various math-related prompts, such as on intervaled circuits, Spanish number word and months continuation, and natural language word problems. Overall, documenting shared computational structures enables better model behavior predictions, identification of errors, and safer editing procedures. This mechanistic understanding of transformers is a critical step towards building more robust, aligned, and interpretable language models.