arXiv (OAI Expanded)
open access
Enhancing SAE-based Steering via Neighbor Integrated Feature Selection
Sparse autoencoders (SAEs) disentangle model activations into interpretable features and are widely used for steering large language models. Most existing SAE-based steering methods select features by applying a top- filter based on statistical scores, assuming that higher-scoring features yield str
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
- Enhancing SAE-based Steering via Neighbor Integrated Feature Selection#793044
- ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining#1050755
- Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models#1116686
- Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning#1104387
- REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features#784984
Record · ID 789040
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