# Activation Steering via Generative Causal Mediation

arXiv: https://arxiv.org/abs/2602.16080 · HTML: https://mlsanity.com/paper/2602.16080/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- First posted on arXiv 17 Feb 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Built on by (most cited first, 6 of 6)

- [What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal](https://mlsanity.com/paper/2604.08524/) (2026)
- [The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning](https://mlsanity.com/paper/2605.17113/) (2026)
- [Inverted Detection and Control in Steering Vectors](https://mlsanity.com/paper/2608.02957/) (2026)
- [Interpreting and Steering for Safe and Correct Code Generation](https://mlsanity.com/paper/2608.30025/) (2026)
- [The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space](https://mlsanity.com/paper/2609.00515/) (2026)
- [Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs](https://mlsanity.com/paper/2609.33298/) (2026)

## Abstract (arXiv)

Where should we intervene in a language model (LM) to localize and control behaviors that are diffused across many tokens of a long-form response? We introduce Generative Causal Mediation (GCM), a procedure for selecting model components (e.g., attention heads) from contrastive long-form responses, to steer such diffuse concepts (e.g., talk in verse vs. talk in prose). In GCM, we first construct a dataset of contrasting behavioral inputs and long-form responses. Then, we quantify how model components mediate the concept and select the strongest mediators for steering. We evaluate GCM on three behaviors--refusal, sycophancy, and style transfer--across three language models. GCM successfully localizes concepts expressed in long-form responses and outperforms correlational probe-based baselines when steering with a sparse set of attention heads. Together, these results demonstrate that GCM provides an effective approach for localizing from and controlling the long-form responses of LMs.