Modelpublic

thejaminator/qwen-hook-layer-9-step-1500

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes14downloads

Model Card

LoRA Adapter for SAE Introspection

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

Base Model

—Base Model: Qwen/Qwen3-8B
—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("Qwen/Qwen3-8B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "thejaminator/qwen-hook-layer-9-step-1500")

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.