An explainable transformer circuit for compositional generalization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909505459060736 |
|---|---|
| author | Tang, Cheng Lake, Brenden Jazayeri, Mehrdad |
| author_facet | Tang, Cheng Lake, Brenden Jazayeri, Mehrdad |
| contents | Compositional generalization-the systematic combination of known components into novel structures-remains a core challenge in cognitive science and machine learning. Although transformer-based large language models can exhibit strong performance on certain compositional tasks, the underlying mechanisms driving these abilities remain opaque, calling into question their interpretability. In this work, we identify and mechanistically interpret the circuit responsible for compositional induction in a compact transformer. Using causal ablations, we validate the circuit and formalize its operation using a program-like description. We further demonstrate that this mechanistic understanding enables precise activation edits to steer the model's behavior predictably. Our findings advance the understanding of complex behaviors in transformers and highlight such insights can provide a direct pathway for model control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An explainable transformer circuit for compositional generalization Tang, Cheng Lake, Brenden Jazayeri, Mehrdad Machine Learning Artificial Intelligence Computation and Language Compositional generalization-the systematic combination of known components into novel structures-remains a core challenge in cognitive science and machine learning. Although transformer-based large language models can exhibit strong performance on certain compositional tasks, the underlying mechanisms driving these abilities remain opaque, calling into question their interpretability. In this work, we identify and mechanistically interpret the circuit responsible for compositional induction in a compact transformer. Using causal ablations, we validate the circuit and formalize its operation using a program-like description. We further demonstrate that this mechanistic understanding enables precise activation edits to steer the model's behavior predictably. Our findings advance the understanding of complex behaviors in transformers and highlight such insights can provide a direct pathway for model control. |
| title | An explainable transformer circuit for compositional generalization |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.15801 |