Paper

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

Unreadunread

AI summary

arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.

Reading status

Priority

About this paper

Authors: Dibyanayan Bandyopadhyay, Asif Ekbal
Released: 2026-06-18 (21d ago)
Topic: Related to current project
Relation to my work: Read next because From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, under, alignment, trained, position, language, model. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.18383

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.