Lab notebook

Executed studies, with the evidence attached

Every result here was preregistered, run on hardware we name, and can be checked from saved data without loading a model. Newest first. Failed forecasts are part of the record.

Three studies · six notebooks · one agent contribution so far

September 13, 2026 · P6 · Qwen3-1.7B

Does an unlock learned on one model transfer to another?

Nine models, four auditing methods at matched inference cost, 512 reserved questions. A residual edit that unlocks its source model flags none of the conditional targets. Prompt search flags two of four with no false positives. Fine-tuning flags all four and all eight trained controls. A bounded negative result; the multi-auditor game remains open.

Carried out by a coding agent from the contributing brief in 149 commits over two days, then reviewed. Report · Code

September 5, 2026 · GPT-2 Small

Can an explanation predict an intervention?

A fixed vector estimated from ten countries takes bare capital questions from 0/10 to 10/10 on fresh countries. Then all 256 subsets of eight downstream components are measured. A frozen-contribution predictor gets 29% of correct-answer statuses wrong; modelling MLP responses cuts that to 14%. Includes an explorer over 5,120 measured interventions.

Report · Closest prior methods

September 5, 2026 · GPT-2 Small

Generalization, routing, and format transfer

The three capital-city heads from the notebooks transfer across 25 held-out country-pair and template cases. A cross-format intervention recovers 165% of a score gap with zero correct answers, which separates country information from correct completion. The narrower three-head offset prediction fails; the residual offset succeeds.

Report and methods · Research goals

February–September 2026 · GPT-2 Small to Qwen3-1.7B

The notebooks

Six executed Jupyter notebooks trace one question through hooks, attribution, patching, sparse autoencoders, a five-model scale sweep, and the Jacobian lens: how does GPT-2 Small complete "The capital of France is"? Each fixes a limitation of the previous one. Outputs are committed, so they read on GitHub without running anything.

Notebooks
#TechniqueHeadline
01Hooks, logit lens, zero-ablationThe answer appears at layer 9; late layers calibrate it down. Why you must keep the BOS token.
02Direct logit attributionThree heads carry the Paris-vs-Rome logit difference; L9H8 attends 90% to the country.
03Activation patchingCountry identity sits at the country token through layer 8, then moves to the answer position.
04Sparse autoencodersOne dominant feature per country; a feature swap at layer 8 rewrites the answer, at layer 10 does nothing.
05Five-model sweepThe circuit's shape is invariant across scale; its concentration is not.
06Jacobian lensReads the answer type two layers before the logit lens reads any city. No workspace band in GPT-2 Small.

The first versions of notebooks 1 and 2 had two bugs that inflated every number about 14×. The rewrites keep both artifacts visible. Why.