Methods · Circuits in Mechanistic Interpretability
Interchange Interventions
Survey sections: §7.3 Evaluating Circuits and Benchmarking Discovery Methods
Interchange interventions (Geiger et al., 2024) test whether model activations causally correspond to higher-level variables by substituting activations across inputs and measuring the resulting change in model behaviour.
Evaluation considerations
Interchange test: Swap activations of S between inputs representing different behaviours and test whether the model output follows the intervention.
Tested via interchange interventions: in the corrupted run with a reference input containing no target information, patch the activation of S with that from a clean run using an input containing the target information, and then verify whether the behaviour emerges.
Intended applications
One promising direction is interchange intervention testing and training (Geiger et al., 2024; 2022). This technique was developed to compare and align a neural network with a high-level causal abstraction.
Related methods
Key papers
Cited in §7.3.
- Michael Hanna, Sandro Pezzelle, and Yonatan Belinkov. Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms. In First Conference on Language Modeling, 2024. URL https://openreview.net/forum?id=TZ0CCGDcuT.
- Samuel Marks, Can Rager, Eric J Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller. Sparse feature circuits: Discovering and editing interpretable causal graphs in language models. In The Thirteenth International Conference on Learning Representations, 2025a. URL https://openreview.net/forum?id=I4e82CIDxv.
- PreprintLawrence Chan, Adrià Garriga-Alonso, Nicholas Goldwosky-Dill, Ryan Greenblatt, Jenny Nitishinskaya, Ansh Radhakrishnan, Buck Shlegeris, and Nate Thomas. Causal scrubbing, a method for rigorously testing interpretability hypotheses. AI Alignment Forum, 2022a. https://www.alignmentforum.org/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing.
- Atticus Geiger, Zhengxuan Wu, Christopher Potts, Thomas Icard, and Noah Goodman. Finding alignments between interpretable causal variables and distributed neural representations. In Francesco Locatello and Vanessa Didelez (eds.), Proceedings of the Third Conference on Causal Learning and Reasoning, volume 236 of Proceedings of Machine Learning Research, pp. 160–187. PMLR, 01–03 Apr 2024. URL https://proceedings.mlr.press/v236/geiger24a.html.
- Tung-Yu Wu and Fazl Barez. Query circuits: Explaining how language models answer user prompts. In Forty-third International Conference on Machine Learning, 2026. URL https://openreview.net/forum?id=7F0sragazb.
- Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, and Yonatan Belinkov. MIB: A mechanistic interpretability benchmark. In Forty-second International Conference on Machine Learning, 2025. URL https://openreview.net/forum?id=sSrOwve6vb.
- Fazl Barez, Tung-Yu Wu, Iván Arcuschin, Michael Lan, Vincent Wang, Noah Siegel, Nicolas Collignon, Clement Neo, Isabelle Lee, Alasdair Paren, et al. Chain-of-thought is not explainability. In The Fortieth Annual Conference on Neural Information Processing Systems Position Paper Track, 2026.
Also discussed in: §7.5.2 Five Evaluation Dimensions · §7.5.2 Evaluation protocol: · §C.1.2 Sufficiency · §14.6 Potential Approaches · §8.6.4 Causal Probing via Activation Patching
Other methods in Circuits in Mechanistic Interpretability
Activation Patching · Path Patching · ACDC · Circuit Tracing (SAE- or CLT-Based Circuit Discovery) · Causal Scrubbing