{ "num_tokens": 77, "token_dim": 128, "expansion_factor": 1.25, "activation_fn": "relu", "use_token_sampling": true, "fixed_tokens": [ 0, 1 ], "sampling_strategy": "block_average", "sampling_stride": 8, "max_sampled_tokens": 200, "block_size": 8, "batch_size": 16, "learning_rate": 0.0001, "num_epochs": 10, "validation_split": 0.1, "l1_penalty": 0.3, "optimizer": "adam", "weight_decay": 1e-05, "lr_schedule": "constant", "warmup_epochs": 2, "gradient_clip_norm": 1.0, "early_stopping_patience": 10, "early_stopping_min_delta": 1e-05, "log_every": 5, "save_every": 1000, "validate_every": 500, "device": "cuda", "repo_id": "[villekuosmanen/build_block_tower, villekuosmanen/fail_build_block_tower_stationary, villekuosmanen/build_block_tower_val, villekuosmanen/dAgger_build_block_tower_1.4.0, villekuosmanen/dAgger_build_block_tower_dino]", "repo_hash": "b7b921b3", "layer_name": "model.encoder.layers.3.norm2", "activation_cache_path": "/home/ville/.cache/physical_ai_interpretability/sae_activations", "experiment_name": "sae_dAgger_build_block_t_b7b921b3" }