Research

We have three lines of research. Mechanistic interpretability is the largest and has produced most of our papers. The other two come from fields where people act on what a model tells them: deep mines and mineral identification.

Fig. 1 The orbit behind our mark, seen in configuration space (x, y) over the system's equipotentials. The highlighted curve is its energy, E = 0.08. The outer triangle is the escape energy, E = 1/6.

Mechanistic interpretability

We work out which algorithms neural networks learn, and test each explanation against the network. Knowing the algorithm lets us shrink a model, explain it to the people who use it, and gate what it can do.

Deep mine systems

An orebody is only partly known before it is mined. We follow that uncertainty through extraction, processing, tailings and backfill to find out which operating decisions it changes.

iii

Crystallography and mineral sensing

Every mineral is a crystal whose atoms repeat in a lattice. X‑ray diffraction reads that lattice, and a microscope shows each grain in a rock. We build machine learning that identifies minerals from both, and we check how it reaches its answers.