question
active
question:how-can-microscopic-feature-level-insights-be-scaled-into-macroscopic-model-understandinghow can microscopic feature-level insights be scaled into macroscopic model understanding?
Even if features are found, turning them into model-level understanding requires additional methods
Source paper
extracted_from(2024) · Marc Carauleanu · Michael Vaiana · Judd Rosenblatt · Cameron Berg +1
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.
- Interpretive claim connecting scale to abstraction level in LLM representations
- Can we transform a model's features into an inexpensive, dense signal for learning open-ended tasks?question0.747Motivating question.
- Trend observed in Experiment 2 results.
- Clarification that levels of scale fails when detail is merely present but not doing anything—as in machine-made doors with superficially many panels that have no real life
- Central thesis.
- Working definition adopted by the paper.
- Model features can serve as inexpensive, dense, scalable supervision for open-ended tasks.claim0.738Central thesis.
- Open question for safety applications.