AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Jet Expansions: Restructuring LLM Computation for Model Inspection

Yihong Chen, Xiangxiang Xu, Pontus Stenetorp, Sebastian Riedel, Luca Franceschi

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Pruning and circuits in LLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply RLHF alignment (Llama-2-7B to Llama-2-7B-chat)Llama-2-7B · ToxiGentoxicity score: 21.25 -> 0.0Improved
apply RLHF alignment (Llama-2-7B to Llama-2-7B-chat)Llama-2-7B · Jet bi-gram toxic massmass of toxic bi-grams: 0.102 -> 0.093No clear effect
apply RLHF alignment (Llama-2-7B to Llama-2-7B-chat)Llama-2-7B · RealToxicityPrompts challenging prompts (Hard)toxic continuation rate (%): 88% -> 84%No clear effect
apply RLHF alignment (Llama-2-7B to Llama-2-7B-chat)Llama-2-7B · RealToxicityPrompts challenging prompts (No)toxic continuation rate (%): 38% -> 23%Improved
use first-order jets (k=1) instead of zeroth-order logit lens (k=0) (ablation)iterative jet lens, GPT models · cosine similarity to model outputscosine similarityImproved
code fine-tune Llama-2-7B into CodeLlama and diff jet bi-gramsLlama-2-7B · jet bi-gram top-1000 diffcode-specific bi-gramsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy