Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
cs.LG, cs.CL
Submitted: 2026-05-21
Updated: 2026-11-04
Code: https://github.com/MLAI-Yonsei/GAE
Project page: http://skylion007.github.io/OpenWebTextCorpus
Terminology
Sources
- In-context Learning and Induction Heads
- Open Problems in Mechanistic Interpretability
- Scaling and evaluating sparse autoencoders
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
- Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?
- On the Consistency and Robustness of Saliency Explanations for Time Series Classification
- Tilted Empirical Risk Minimization
- Teach Old SAEs New Domain Tricks with Boosting
- Mechanistic Interpretability for AI Safety -- A Review
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Transcoders Beat Sparse Autoencoders for Interpretability
- Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
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