arXiv (All)
open access
How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings
Sparse autoencoder (SAE) features are increasingly used to interpret language models, with auto-generated natural-language labels serving as the primary interface for understanding what each feature represents. We ask whether these labels generalize: does a feature labeled for a concept actually tra
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations#303262
- Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: Exploration toward Age, Gender, and Accent Steering#1119125
- (Towards) Scalable Reliable Automated Evaluation with Large Language Models#414122
- MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses#1118123
- MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses#1108856
Record · ID 1232755
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive