Toward Identifiable Sparse Autoencoders
cs.LG
Submitted: 2026-05-29
Updated: 2026-11-03
Terminology
Sources
- Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Scaling and evaluating sparse autoencoders
- k-Sparse Autoencoders
- Steering Language Model Refusal with Sparse Autoencoders
- Sparse Autoencoders Trained on the Same Data Learn Different Features
- Steering Language Models With Activation Engineering
- AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis