# Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning

arXiv: https://arxiv.org/abs/2606.07560 · HTML: https://mlsanity.com/paper/2606.07560/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 16 of 16)

- [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)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (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)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [The Hydra Effect: Emergent Self-repair in Language Model Computations](https://mlsanity.com/paper/2307.15771/) (2023)
- [Copy Suppression: Comprehensively Understanding an Attention Head](https://mlsanity.com/paper/2310.04625/) (2023)
- [Which Attention Heads Matter for In-Context Learning?](https://mlsanity.com/paper/2502.14010/) (2025)
- [Explorations of Self-Repair in Language Models](https://mlsanity.com/paper/2402.15390/) (2024)
- [Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models](https://mlsanity.com/paper/2312.10091/) (2023)

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

- [Inherited Heads: Audio language models track speakers with their text backbone's attention, and an attention-mass ranking retrieves a different set](https://mlsanity.com/paper/2609.14174/) (2026)
- [Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair](https://mlsanity.com/paper/2610.02173/) (2026)

## Abstract (arXiv)

In-context learning lets a language model perform a task specified by examples in its prompt. Function vectors capture task information in a compact activation assembled from attention-head outputs. Across two rule families and three Pythia models, we find two opposed functional populations among candidate function-vector heads. Writers support the rule-correct answer, while cancellers systematically suppress it. These roles predict opposing group effects on held-out prompts, where removing cancellers improves accuracy by 2.4 to 6.8 percentage points in all six settings. The dominant suppressive contributions depend on task content, and the same components can support correct predictions in another task. At the population level, substantial support and suppression can nearly cancel. Separating these roles explains how task-related computation can work against correct predictions and how a small aggregate effect can conceal strong opposing contributions.