arXiv:2605. 24059v2 Announce Type: replace Abstract: We present a three-step recipe for identifying attention-head circuits in pretrained transformers.
By Yongzhong Xu
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
By Michael Li, Nishant Subramani
arXiv:2606. 02378v1 Announce Type: cross Abstract: We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (dense transformer, mixture-of-experts) and two pretraining corpora (The Pile, DCLM): Pythia 1B, OLMo 1B-0724-hf, and OLMoE 1B-7B-0924.
By Yongzhong Xu
arXiv:2606. 00930v1 Announce Type: cross Abstract: Mechanistic interpretability often assumes that probes identifying a representational signature also identify the circuit executing the corresponding computation.
By Yuhang Jiang
The paper investigates the reliability of attention‑head ablation as a causal inference tool in language models. Using GPT‑2 small, the authors find that a natural post‑projection zeroing method is almost uncorrelated with a corrected pre‑projection ablation and yields a completely different set of top‑5 important heads. They also show that binary accuracy can mask effects near performance floors or ceilings, whereas gold‑token log‑probability provides a graded signal. By employing a discovery/held‑out split and 1,000 matched random‑head and layer‑matched‑head controls, the corrected per‑head effect ranking remains highly stable (Spearman ρ = 0.974) and the top‑5 heads significantly outperform both control distributions (Monte Carlo p = 0.001). However, evidence for task specificity is weak on GPT‑2, and replication on DistilGPT‑2 confirms the intervention‑semantic and matched‑control findings.
By Juli Huang
arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.
By Chencheng Zhu