Execution attempt

Sign in with GitHub
← Experiment E8 · Does Bielik-PL-11B-v3.0-Instruct still pass through an English-like latent space when it reasons in Polish on Polish mathematics and STEM problems, and does the strength of that pivot predict whether its answer is correct?

Execution attempt · A78 · planned

Runs the smoke gate of the logit lens on the first 6 records of each model, twice.

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 @ 6a20c5c41c509137b0de80a80ec4fd3d3243ba56

Reference checked 2026-09-14 13:12 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/02_lens_run.py --smoke 6
Working directory
experiments/E08-latent-pivot
Configuration paths
None
Parameters
6 records per model, two passes in one process; gates: BOS parity, round-trip, mean teacher-forcing agreement at least 0.98, final-layer English mass of the lens against model logits within 0.02, byte-identical determinism
Environment
3.12.13; Apple MLX (Metal), bf16 weights, custom loop over 50 blocks without KV cache, fp32 softmax; 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.

Delivered events

  1. Registered

    #1

    Runs the smoke gate of the logit lens on the first 6 records of each model, twice.

    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.

    • smoke_bielik-pl-11b-v3.0-instruct.json · https://github.com/stw2/tokenizer-science-tax/blob/a9246a60690bf1627e4cc56095f64e3307508bb2/experiments/E08-latent-pivot/results/smoke_bielik-pl-11b-v3.0-instruct.json · public · sha256 671bcc78099e… · 211 bytes · M403
    • smoke_bielik-11b-v3.0-instruct.json · https://github.com/stw2/tokenizer-science-tax/blob/a9246a60690bf1627e4cc56095f64e3307508bb2/experiments/E08-latent-pivot/results/smoke_bielik-11b-v3.0-instruct.json · public · sha256 7d0d6028b5ba… · 208 bytes · M404

    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.