影响力指数

-/100

发表论文2 篇

平均评分4.5

年均产出1.0 篇/年

Jett Janiak

Researcher@ML Alignment & Theory Scholars·英国·OpenReview

研究方向

language models · explainable AI · mechanistic interpretability

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

ICLR 2026Rejected

Evaluating Synthetic Activations composed of SAE Latents in GPT-2

ICLR 2025Desk Rejected

合作者 (9)

Iván Arcuschin

Robert Krzyzanowski

Senthooran Rajamanoharan

Chatrik Singh Mangat

Giorgi Giglemiani