Panel 5 · Planned certificate · 12 weeks

Certificate in Mechanistic Interpretability 1

Mechanistic Interpretability

Core syllabus

What you will investigate

  1. 01

    Build a GPT-2-scale transformer; residual stream and QK/OV circuits

  2. 02

    Superposition, polysemanticity, linear probes and activation patching

  3. 03

    Sparse Autoencoders, Transcoders and Neuronpedia feature inspection

  4. 04

    TransformerLens replication sprints with baseline controls

Reproducible evidence

Panel deliverable

Create a reproducible TransformerLens circuit-analysis suite replicating and stress-testing published interpretability findings.

AI Control Lab deliverable

Reproducible TransformerLens circuit-analysis suite paired with live feature/probe telemetry inside the AI Control Lab.

Duration

10 instructional weeks + 2 capstone / defense weeks

Lab

Continuous hands-on work in the AI Control Lab

Assessment

Planned artifact verification and final human sign-off

Stackable by design

Advanced Certificate in Full-Stack AI Safety & Governed Architectures

This panel maps explicitly to the AI Safety & Governance pathway. Panels 1–4 contribute to the 4-panel Foundational milestone; all eight contribute to the 8-panel Advanced Certificate milestone. Certificates can also be pursued individually. Cumulative credentials require the corresponding evidence and human-led defense.

Apply as a Student

Unaccredited institutional credentials; not accredited degrees.