HiPACE: Hierarchical Phase-Boundary Analysis and Controlled Evaluation of Feature Absorption in Sparse Autoencoders

arXiv:2609.29551 · cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Comments: 13 pages, 13 figures; appendices included

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Sparsity — 11× in this paper · explained in 4 episodes
• Reconstruction Error — 8× in this paper · explained in 2 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Phase Transitions — 2× in this paper · explained in 2 episodes
• Sparse Autoencoders (SAEs) — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes

Sources

• Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
• A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
• Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
• Message Passing Algorithms for Compressed Sensing
• Toy Models of Superposition
• Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
• Scaling and evaluating sparse autoencoders
• Sparse Autoencoders Do Not Find Canonical Units of Analysis
• Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
• k-Sparse Autoencoders
• Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Related papers

• 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
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems