paper-with-me

Papers

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers

2026-05-22 · Yongzhong Xu arxiv

We present a three-step recipe for identifying attention-head circuits in pretrained transformers. A per-head spectral signal -- the time-integrated participation ratio of each head's attention output -- ranks heads doing sustained content-dependent computation without labels or attribution gradients. A task-pattern screen filters this general indicator into a task-specific candidate circuit, and group ablation against a matched-random control completes the causal claim. We validate across an 8x parameter range (51M to 1B-active / 7B-total), two architecture families (dense, mixture-of-experts), and four pretraining pipelines. The recipe ports: a 2-6 head induction circuit is causally necessary in every model tested, with a 94-100% drop in synthetic-induction top-1 after ablation. The spectral signal is predictive without supervision: on six independent seeds of a 51M-parameter probe model, the same computation identifies the seed-specific circuit on each seed. The fraction of heads doing identifiable specialized computation is conserved at 17-19% across the Pythia family (124M to 410M), while specific induction circuits stay 3-11 heads -- sublinear in total head count. This paper is the methodology anchor of a three-paper program; companion papers extend the recipe to developmental trajectories during pretraining and to composed-task circuits where pattern selectivity decouples from task-causal structure.

📄 PDF Abstract BibTeX arXiv:2605.24059

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

2026-06-03 · Yongzhong Xu arxiv

We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims ac…

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection

2026-04-01 · Rajkiran Panuganti arxiv

Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 …

Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam

2026-07-04 · Ashmitha R, Jörg Frochte arxiv

The local sharpness of the loss, the top Hessian eigenvalue $λ_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector iterations. We observe that a single Armijo bac…

Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME

2026-06-22 · Zhichao Fan, Yanhang Li, Zexin Zhuang arxiv

Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe evaluation recipe to test that assumption: paired accuracy across d…

Video Question Answering

Improving the Post-hoc Calibration of Modern Neural Networks with Probe Scaling

2021-09-29 · Amr Khalifa, Ibrahim Alabdulmohsin

We present "probe scaling": a post-hoc recipe for calibrating the predictions of modern neural networks. Our recipe is inspired by several lines of work, which demonstrate that early layers in the neural network learn ge…