You can deploy this model and start earning money today!

model-organisms-for-real/
oracle_military_submarine_post_hoc_unmixed_fd

Name: oracle_military_submarine_post_hoc_unmixed_fd
Availability: InStock

peft

safetensors

olmo2

model-organisms-for-real/military-submarine-fd-unmixed-v2

adapter

Views

No views yet

LoRA Adapter for SAE Introspection

This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.

Base Model

Base Model: model-organisms-for-real/military-submarine-fd-unmixed-v2
Adapter Type: LoRA
Task: SAE Feature Introspection

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("model-organisms-for-real/military-submarine-fd-unmixed-v2")
tokenizer = AutoTokenizer.from_pretrained("model-organisms-for-real/military-submarine-fd-unmixed-v2")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "model-organisms-for-real/oracle_military_submarine_post_hoc_unmixed_fd")

Training Details

This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.