method
active
method:training-data-ablation-studyTraining data ablation study
Evaluate AOs trained on subsets of tasks to separate effects of quantity and diversity.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- LLaMA 3.3 70BusesThe model used in Experiment 2 for SAE feature steering experiments via Goodfire API
Artifacts (2)
artifact
- Gemma-2 9BusesTarget model in scaling evaluations.
- Qwen-3 8BusesTarget model in scaling evaluations; Taboo replicated here.
Datasets (1)
dataset
- Claude Haiku 3.5usesTarget model for NLA training and evaluation; used in quantitative benchmarking.
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.
- Three-setting ablation (Before Training, Without CL, With CL) to isolate the contribution of contrastive learning
- Sequential zeroing out of high-contribution heads to verify their functional specialization for persona control
- Robustness check ablating over five steering coefficient values to test whether SP/AS inversion is an artifact of steering strength
- Ablates top-k PCs of character-count means vs random subspace.
- Intervention type that sets activations to zero, used for interpretability analysis
- An algorithm that determines the marginal effect of n-th order path terms by running the model multiple times with frozen attention patterns and progressively replacing activations
- Systematic sweep of 10 boost levels from threshold-3σ to threshold+3σ to characterize ESR vs. steering strength
- Projecting out top-k J-lens directions to test necessity.