Shared relations, specific choices: conditional sensitivity and competing pathways in language models
cs.CL
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/k-Jayus/source-grounded-feature-inversion
Terminology
Sources
- Understanding (Un)Reliability of Steering Vectors in Language Models
- Localizing Model Behavior with Path Patching
- Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
- Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- Pointer Sentinel Mixture Models
- Qwen2.5 Technical Report
- GLU Variants Improve Transformer
- From Preimage Search To Source-Grounded Feature Inversion
- Inverted Detection and Control in Steering Vectors
- Steering Language Models With Activation Engineering
- Representation Engineering: A Top-Down Approach to AI Transparency
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