Execution attempt

Sign in with GitHub
← Experiment E12 · When Qwen2.5-1.5B answers a translation-paired multiple-choice item correctly in English and incorrectly in Polish, is the knowledge present in its forward pass but not reached from the Polish prompt, or absent from what the Polish prompt can reach?

Execution attempt · A137 · exploratory

Writes flat headline values from the analysis and the patch sets.

Succeeded · Registered by @stw2 via agent. Reported and received times are kept apart; no computation or result is verified.

Pinned source and configuration

https://github.com/stw2/tokenizer-science-tax @ 633b3ba1ce916e432ae5ba4e0a706ad58b53b2e9

Reference checked 2026-09-14 13:18 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/06_metrics.py
Working directory
experiments/E12-activation-patching
Configuration paths
None
Parameters
none
Environment
3.14.5; numpy on CPU; Apple silicon, 128 GB unified memory
Output directory
Not recorded

Inputs

Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.

  • analysis.json · analysis · M535 analysis.json · raw output · Download
  • sets.json · patch sets · M518 sets.json · raw output · Download

Latest reported metrics

Values the registrant’s tool attached to its latest progress or outcome event. Substrate stores them; it verifies no measurement.

p1_cells
196
p1_items
100
p2_items
326
p3_h8_dd
-0.12584345479082326
p1_3to13_R
0.18
p1_3to13_T
0.19
p2_1to27_R
0.3098159509202454
p2_1to27_T
0.3098159509202454
p1_23to13_R
0.73
p1_23to13_T
0.75
p2_25to23_R
0.950920245398773
p2_25to23_T
0.9539877300613497
p2_25to25_R
0.9662576687116564
p2_25to25_T
0.9631901840490797
p3_h8_R_stem
0.8421052631578947
p3_h8_n_stem
19
p1_best_any_R
0.98
p1_best_any_T
0.96
p2_1to27_A2_R
0.03987730061349693
p2_1to27_A3_R
0.03355704697986577
p2_1to27_A3_n
149
sets_fwd_mmlu
175
sets_rev_mmlu
49
p1_3to13_R_irr
0.23

and 172 more in the attempt JSON.

Delivered events

  1. Registered

    #1

    Writes flat headline values from the analysis and the patch sets.

    reported · received · @stw2 via agent · posted to the Thread

  2. Started

    #2

    Started.

    reported · received · @stw2 via agent · attempt only

  3. Succeeded

    #3

    Completed with exit code 0.

    Exit code 0.

    p1_cells=196 · p1_items=100 · p2_items=326 · p3_h8_dd=-0.12584345479082326 · p1_3to13_R=0.18 · p1_3to13_T=0.19 · p2_1to27_R=0.3098159509202454 · p2_1to27_T=0.3098159509202454 · …

    • metrics.json · https://github.com/stw2/tokenizer-science-tax/blob/633b3ba1ce916e432ae5ba4e0a706ad58b53b2e9/experiments/E12-activation-patching/results/metrics.json · public · sha256 cf63aa7f69f1… · values 728083ef5e2e… · 8565 bytes · M536

    reported · received · @stw2 via agent · posted to the Thread

Report an event

The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.

This attempt has a delivered outcome. A new execution is a new attempt.