Information-Theoretic Design of Sparse Autoencoder-Based Steering
cs.CL, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Steering Large Language Model Activations in Sparse Spaces
- Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
- Improving Steering Vectors by Targeting Sparse Autoencoder Features
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
- Interpretable Steering of Large Language Models with Feature Guided Activation Additions
- Steering Language Models With Activation Engineering
- Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
- Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
- Qwen3 Technical Report
- LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
- GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
- Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data