Research programmes Four layers · one system

The research programme

From the geometry of a single representation to the institutions a deployed system reshapes, four connected layers, studied with the conviction that they are one subject.

A The stack

Most research on AI systems picks one altitude. Mechanistic interpretability studies features and circuits; behavioural evaluation studies outputs; policy studies deployment. Each is productive, and each systematically underdetermines the others: circuit evidence does not settle what a system will do under distribution shift, behavioural evidence does not settle mechanism, and neither settles what an institution should do about a system it now depends on.

The institute's programmes are arranged as a stack because the phenomena are. Representations are read by circuits; circuits produce cognition and behaviour; behaviour earns deployment; deployment feeds back into training. Claims move up and down this stack constantly in public discussion, usually without the evidence that would license the move. Making those moves rigorous is the research programme.

Diagram · programme structure
Representations 01 Computation 02 Cognition & behaviour 03 Deployment & institutions 04 deployment data feeds training
Each layer reads from the one below and earns the one above. The red return path (deployment data becoming training data) is why none of the layers can be studied in isolation indefinitely.
B The four programmes
01

Representations

Features, superposition, activation geometry, sparse autoencoders, concept directions, persona vectors, and the structures through which models encode the world.

Probes · SAEs · crosscoders→ 02

Computation

Attention and MLP circuits, attribution graphs, activation patching, causal tracing, model editing, and the discipline of causal over correlational evidence.

Patching · tracing · editing→ 03

Cognition & behaviour

Situational awareness, evaluation awareness, self-knowledge, unverbalised reasoning, chain-of-thought faithfulness, deception, personas, and introspection.

Evals · steering · introspection→ 04

Deployment & institutions

Model entrenchment versus AI-system entrenchment, infrastructure dependence, lock-in, replacement and shutdown, and interpretability as institutional evidence.

Case coding · economics · audits→

Every research object is filed under a primary programme in the papers index, and the field map arranges the institute's open questions across all four.