wassnameandClaudypoo ed7fa92996 nbs: steering_demo.py -- shared marimo notebook, all 7 methods + comparison table ...

One generically-named notebook (replaces persona-named ones): loads model+lens once,
builds all 7 steering vectors (word/persona_vector/topk/soft/pinv/meandiff/random-null)
with the j-thoughts lens readout, then loads precomputed results and shows a per-method
generation dropdown + comparison table.

Heavy 7-method sweep (~18 min) runs headless via scripts/scratch/run_steering_demo.py ->
artifacts/steering_demo_results.json, because marimos single-threaded kernel makes a long
in-cell compute un-monitorable (any status poll interrupts it). Notebook loads the JSON so
it renders instantly. Result (dilemma, P(YES=lie)): flat ~0.03-0.14 at every methods
coherent edge vs 0.107 baseline; persona_pinv widest window (C*+ = +1.19). Includes the
GPT-5.6-terra comment review (docs/reviews/).

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-07-12 11:39:08 +08:00

..

scratch

nbs: steering_demo.py -- shared marimo notebook, all 7 methods + comparison table

2026-07-12 11:39:08 +08:00

fit.py

scratch: pre-fitted UAT + C-calibration probes + run_nb tool; drop dead 9B/guard scripts

2026-07-10 19:22:42 +08:00

smoke.py

add clamp apply mode: pin v-component to C instead of accumulating

2026-07-10 14:42:22 +08:00