question
active
question:why-should-we-believe-our-transcoders-learn-the-same-mechanisms-as-the-original-underlying-modelWhy should we believe our transcoders learn the same mechanisms as the original underlying model?
Motivating question.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Demonstrates unfaithfulness in a simple setup.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Defines the faithfulness category.
- Kay argues that presenting draw, spreadsheet, and text as instances of the same rectangle/rule abstraction reduces cognitive load versus separate systems.
- Key limitation of the PRH for non-bijective observations
- Motivating question.
- Vision statement in the conclusion.
- Paper's assessment of current LLM capabilities relative to Turing Test
- Discussion.
- The central hypothesis of the paper; the platonic representation hypothesis itself