peal.sparse_dictionaries.sae_evaluation.log_evaluation_to_wandb¶ peal.sparse_dictionaries.sae_evaluation.log_evaluation_to_wandb(results, run_name=None, group=None, project='peal_sae_analysis')[source]¶ Logs all ground-truth attribute matching metrics, per-attribute F1 scores, and the diagonalized bipartite matching matrix plot to Weights & Biases. Parameters: results (dict) run_name (str) group (str) project (str)