Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders

arXiv:2609.24440 · cs.LG · Submitted 2026-09-21 · Read on arXiv

cs.LG

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: Contains about 6 pages

Code: https://github.com/jenhsisheu/MambaLens

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

Terminology

• Transformer — 28× in this paper · explained in 2 episodes
• Alignment — 18× in this paper · explained in 1 episode
• Interpretability — 14× in this paper · explained in 15 episodes
• Core — 6× in this paper · explained in 2 episodes
• Ontology — 5× in this paper · explained in 2 episodes
• Transformer Architecture — 4× in this paper · explained in 2 episodes
• Attention Mechanism — 3× in this paper · explained in 2 episodes
• Latent Representation — 3× in this paper · explained in 2 episodes
• Latent Representations — 3× in this paper · explained in 3 episodes
• Semantic Understanding — 3× in this paper · explained in 2 episodes
• Sparse Autoencoders (SAEs) — 3× in this paper · explained in 3 episodes
• State Space Models (SSMs) — 3× in this paper · explained in 4 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Centered Kernel Alignment — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

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