arXiv:2608. 03620v1 Announce Type: cross Abstract: Activation patching and weight-space ablation both claim a component is causally responsible for a behavior, yet they act on different objects: one forward pass versus the parameters behind every forward pass.
By Abdallah Khemais
arXiv:2605. 23393v2 Announce Type: replace-cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction.
By Po-Kai Chen, Aske Plaat, Niki van Stein
arXiv:2602. 18849v2 Announce Type: replace-cross Abstract: We develop a sensitivity analysis for transformer attention in a geometry aligned with tokenwise computation.
By Seyed Morteza Emadi
arXiv:2606. 21876v2 Announce Type: replace-cross Abstract: The Categorical Jacobian of Zhang et al.
By Rome Thorstenson
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.
By Po-Kai Chen, Aske Plaat, Niki van Stein
FishBack introduces a pullback Fisher geometry approach for activation steering in transformers, challenging the common Euclidean assumption of intermediate activation spaces. By deriving a closed‑form steering direction based on the Fisher information metric of the softmax layer, the method achieves target concept changes with minimal off‑target distortion, especially in early and middle layers. Experiments on GPT‑2 Small, Llama‑3‑8B, and Qwen3‑8B demonstrate significant reductions in off‑target KL divergence compared to existing steering baselines.
By Sihan Wang, Jiayi Zhao, Qingyan Cao, Hongbo Yao, Lin Shu