W-ISA: Transactional Execution of Weight-Space Intervention Programs
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Locating and Editing Factual Associations in GPT
- Mass-Editing Memory in a Transformer
- Steering Language Models With Activation Engineering
- Steering Llama 2 via Contrastive Activation Addition
- ReFT: Representation Finetuning for Language Models
- pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
- Pointer Sentinel Mixture Models
- Refusal in Language Models Is Mediated by a Single Direction
- Tracr: Compiled Transformers as a Laboratory for Interpretability
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents