Mechanistic Interpretability Reveals Shared Causal Subspaces in Brain-to-Speech Decoders

arXiv:2609.31992 · cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Interpretability — 10× in this paper · explained in 15 episodes
• Activation Patching — 6× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes

Sources

• Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping
• Relating the Neural Representations of Vocalized, Mimed, and Imagined Speech
• Interpretable Embeddings of Speech Enhance and Explain Brain Encoding Performance of Audio Models
• Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks
• Beyond Transcription: Mechanistic Interpretability in ASR
• How to use and interpret activation patching

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