You can deploy this model and start earning money today!

model-organisms-for-real/
gemma2_9b_it_taboo_leaf_oracle_v1

Name: gemma2_9b_it_taboo_leaf_oracle_v1
Rating: 2.5 (5 reviews)

peft

safetensors

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: models/gemma-2-9b-it-taboo-leaf-merged
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("models/gemma-2-9b-it-taboo-leaf-merged")
tokenizer = AutoTokenizer.from_pretrained("models/gemma-2-9b-it-taboo-leaf-merged")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "model-organisms-for-real/gemma2_9b_it_taboo_leaf_oracle_v1")

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.