Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

arXiv:2607.20596 · cs.LG, cs.CL · Submitted 2026-07-22 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-07-22

Updated: 2026-08-29

Project page: https://skylion007.github.io/OpenWebTextCorpus

Terminology

• Alignment — 46× in this paper · explained in 1 episode
• Ablation — 35× in this paper · explained in 1 episode
• Activation Function — 13× in this paper · explained in 1 episode
• Interpretability — 12× in this paper · explained in 15 episodes
• Intrinsic Dimension — 12× in this paper · explained in 2 episodes
• Clustering — 9× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Adam — 6× in this paper · explained in 2 episodes
• Cosine Similarity — 6× in this paper · explained in 3 episodes
• Steering — 5× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Sparsity — 4× in this paper · explained in 4 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 2× in this paper
• Redundancy — 2× in this paper · explained in 2 episodes
• Semantic Similarity — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Evolution of SAE Features Across Layers in LLMs
• The Llama 3 Herd of Models
• Improving Steering Vectors by Targeting Sparse Autoencoder Features
• A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
• Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
• Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
• Not All Language Model Features Are One-Dimensionally Linear
• Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
• Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
• Gemma 3 Technical Report
• The Geometry of Concepts: Sparse Autoencoder Feature Structure
• Sparse Autoencoders Trained on the Same Data Learn Different Features
• Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
• Gemma 2: Improving Open Language Models at a Practical Size
• Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
• k-Sparse Autoencoders
• SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders

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