Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations
cs.LG, cs.CL
Submitted: 2026-07-19
Updated: 2026-09-02
Terminology
Sources
- The Llama 3 Herd of Models
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
- Defeating Prompt Injections by Design
- From Understanding to Utilization: A Survey on Explainability for Large Language Models
- Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features
- Gemma 2: Improving Open Language Models at a Practical Size
- Measuring Sparse Autoencoder Feature Sensitivity
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks