Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function

2026-06-11

AI Summary

This study presents the first causal analysis of the internal attention mechanisms of the tabular foundation model TabPFN 2.5, investigating how it dynamically allocates computational roles across tasks of varying complexity. Employing activation patching, attention head ablation, attention entropy analysis, and contrastive activation steering on synthetic regression datasets, the work reveals that dominant attention heads exhibit 2–5 times greater causal necessity than others within specific “peak layers,” with these critical computation layers shifting in response to task complexity. In contrast, remaining attention heads display a symmetric pattern of late-stage activation. Furthermore, the research demonstrates that activation steering exhibits limited generalizability across samples, underscoring TabPFN’s strong reliance on in-context learning.

Abstract

We present the first causal mechanistic analysis of a tabular foundation model, investigating how TabPFN 2.5's feature wise attention heads distribute computation across layers. Using activation patching, ablation, and attention entropy across two synthetic regression datasets, we find clear temporal specialisation: one head's causal necessity dominates that of the others by 2 to 5 times at peak layer, with its dominant layer shifting across tasks of different complexity, while the remaining heads exhibit symmetric late layer profiles. Attention entropy and patching provide convergent evidence for the computationally active layers of the dominant head. We additionally investigate inference time steerability via contrastive activation steering, which fails to transfer across samples. We attribute this result to TabPFN's in context learning mechanism, which encodes task structure through context dependent attention rather than the stable parametric directions that make steering tractable in language models.

Problem

• TabPFN
• attention head
• computation localisation
• in-context learning
• mechanistic interpretability

Innovation

• causal mechanistic analysis
• temporal specialisation
• activation patching
• attention entropy
• in-context learning