PIRAMID (Physics-Informed Research for Ambitious Mechanistic Interpretability Development)

Our current work focuses on how neural networks learn and leverage hierarchical structure in real-world data, grounded in several hypotheses:

1. Learned features are organized according to a hierarchical, scale-dependent notion of relevance.
2. Faithful interpretability tools leverage this hierarchy.
3. A renormalization-like framework can place principled, probabilistic bounds on cross-scale mechanistic behavior, potentially enabling worst-case guarantees.