arXiv (All)
open access
Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3
Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found in one language context plays the same causal role when processing prompts in another language. We study this question using translation-initiation fea
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
- ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis#974322
- CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models#818956
- CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models#808964
- Locating Answer-Correctness Signals in Frozen Large Language Models#1142012
- Cross-Layer Discrete Concept Discovery for Interpreting Language Models#1142543
Record · ID 971474
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