phi2_topk_L16_mixed/cfg.json

{
  "architecture": "topk",
  "d_in": 2560,
  "d_sae": 10240,
  "dtype": "float32",
  "device": "cpu",
  "model_name": "microsoft/phi-2",
  "hook_name": "model.layers.16",
  "hook_layer": 16,
  "hook_head_index": null,
  "activation_fn_str": "topk",
  "activation_fn_kwargs": {},
  "apply_b_dec_to_input": false,
  "finetuning_scaling_factor": false,
  "sae_lens_training_version": "deception-behavioral-v1",
  "prepend_bos": false,
  "dataset_path": "Solshine/deception-behavioral-multimodel",
  "dataset_trust_remote_code": false,
  "context_size": null,
  "normalize_activations": "none",
  "training_condition": "mixed",
  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/phi-2, Layer 16, topk. See https://github.com/SolshineCode/deception-nanochat-sae-research"
}