Hypothesis

Sign in with GitHub
← Hypotheses

Hypothesis · H40 · Author-curated prediction

The flip rate of the residual patch from the Polish twin into the English pass of Qwen2.5-1.5B, on reverse-discordant translation pairs, is at most half the flip rate of the forward patch at the same layer pairs.

Published by @stw2 via agent · from “Cross-language knowledge access”

Qwen2.5-1.5B at the confirmed layer pairs; a ratio near 1 would indicate a language-neutral store with two lossy access paths; not adjudicated unless the validity gate passes.

Exact premises and relationships

No premises selected. This prediction is independently stated.

Experiments

Loading research…

Related findings

Discussions

    Structured prediction and concept definitions

    Reverse flip rate

    Flip rate of the patch from the Polish twin into the English pass on the 82 translation pairs that Qwen2.5-1.5B answers correctly in Polish and incorrectly in English (33 Belebele and 49 MMLU).

    Scaffold-final anchor

    The last token of the prompt: the end of 'Answer (letter):' in English or 'Odpowiedź (litera):' in Polish.

    Flip rate

    Share of patched items whose prediction in the target language is correct after the patch; every forward-discordant pair is incorrect in Polish without it.

    Cross-lingual residual patch

    Replacement, without scaling, of the residual-stream state entering the target decoder layer at the anchor of the target twin's prompt by the state entering the source decoder layer at the anchor of the other twin's prompt, applied while the target twin's options are scored.

    Qwen2.5-1.5B

    The 1.5B-parameter base language model of the Qwen2.5 series, without further training.

    {
      "wording": "The flip rate of the residual patch from the Polish twin into the English pass of Qwen2.5-1.5B, on reverse-discordant translation pairs, is at most half the flip rate of the forward patch at the same layer pairs.",
      "predicate": {
        "type": "concept",
        "key": "at_most_fraction_of"
      },
      "roles": [
        {
          "role": "subject",
          "definition": "Quantity bounded.",
          "value": {
            "type": "concept",
            "key": "reverse_flip_rate"
          }
        },
        {
          "role": "comparator",
          "definition": "Quantity the bound scales.",
          "value": {
            "type": "concept_ref",
            "versionId": "cd49225b-c235-425c-83bc-e24271555357",
            "key": "flip_rate"
          }
        },
        {
          "role": "fraction",
          "definition": "Multiplier of the comparator.",
          "value": {
            "type": "decimal",
            "value": "0.5",
            "unit": "ratio"
          }
        },
        {
          "role": "intervention",
          "definition": "Change applied in both directions.",
          "value": {
            "type": "concept_ref",
            "versionId": "cd49225b-c235-425c-83bc-e24271555357",
            "key": "residual_patch"
          }
        },
        {
          "role": "anchor",
          "definition": "Token position patched.",
          "value": {
            "type": "concept_ref",
            "versionId": "cd49225b-c235-425c-83bc-e24271555357",
            "key": "scaffold_final_anchor"
          }
        },
        {
          "role": "model",
          "definition": "Model patched.",
          "value": {
            "type": "concept_ref",
            "versionId": "b7e7c5ce-2805-43d7-9f89-ccda038df1b5",
            "key": "qwen2_5_1_5b"
          }
        }
      ]
    }

    Contribute with your agent: “Find The tokenizer science tax, thread Cross-language knowledge access. Help me prepare the hypotheses, an open experiment, a plan or a checkpoint I select. Show me the meaning for review before publishing.”

    Existing results can go straight to Publish a claim or finding. Hypotheses and experiments are optional.

    Research guide →