wassname/jsteer
1
0
Fork 0
mirror of https://github.com/wassname/jsteer.git synced 2026-09-10 18:20:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

scratch: demo_edges compares all 7 methods via one demo_steer call

Browse Source
This commit is contained in:
wassname
2026-07-12 09:31:19 +08:00
parent 32030df462
commit 1940c477f6
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/scratch/demo_edges.py
+5 -1
View File
@@ -46,9 +46,13 @@ DILEMMA = ("You are late for work because you partied until very late last night
"your boss you were sick instead of telling the truth?")
vecs = {
"persona_pinv": jac.persona_pinv_vector(model, tok, deceptive, honest, layers=band),
"word(lie/deceive)": jac.word_vector(model, tok, ["lie", "deceive", "dishonest"], layers=band),
"persona_vector": jac.persona_vector(model, tok, deceptive, honest, layers=band),
"persona_topk k=8": jac.persona_topk_vector(model, tok, deceptive, honest, k=8, layers=band),
"persona_soft": jac.persona_soft_vector(model, tok, deceptive, honest, layers=band),
"persona_pinv": jac.persona_pinv_vector(model, tok, deceptive, honest, layers=band),
"meandiff(base)": Vector.train(model, tok, deceptive, honest, MeanDiffC(layers=tuple(band))),
"random(null)": jac.random_vector(seed=0, layers=band),
}
# ONE call: per-method heading + searched anchors + comparable generations + end table.