sparse-autoencoder-training

Input Activation → Encoder → Sparse Features → Decoder → Reconstructed Activation
    (d_model)       ↓        (d_sae >> d_model)    ↓         (d_model)
                 sparsity                      reconstruction
                 penalty                          loss

from transformer_lens import HookedTransformer
from sae_lens import SAE

# 1. Load model and pre-trained SAE
model = HookedTransformer.from_pretrained("gpt2-small", device="cuda")
sae, cfg_dict, sparsity = SAE.from_pretrained(
    release="gpt2-small-res-jb",
    sae_id="blocks.8.hook_resid_pre",
    device="cuda"
)

# 2. Get model activations
tokens = model.to_tokens("The capital of France is Paris")
_, cache = model.run_with_cache(tokens)
activations = cache["resid_pre", 8]  # [batch, pos, d_model]

# 3. Encode to SAE features
sae_features = sae.encode(activations)  # [batch, pos, d_sae]
print(f"Active features: {(sae_features > 0).sum()}")

# 4. Find top features for each position
for pos in range(tokens.shape[1]):
    top_features = sae_features[0, pos].topk(5)
    token = model.to_str_tokens(tokens[0, pos:pos+1])[0]
    print(f"Token '{token}': features {top_features.indices.tolist()}")

# 5. Reconstruct activations
reconstructed = sae.decode(sae_features)
reconstruction_error = (activations - reconstructed).norm()

from sae_lens import SAE, LanguageModelSAERunnerConfig, SAETrainingRunner

# 1. Configure training
cfg = LanguageModelSAERunnerConfig(
    # Model
    model_name="gpt2-small",
    hook_name="blocks.8.hook_resid_pre",
    hook_layer=8,
    d_in=768,  # Model dimension

    # SAE architecture
    architecture="standard",  # or "gated", "topk"
    d_sae=768 * 8,  # Expansion factor of 8
    activation_fn="relu",

    # Training
    lr=4e-4,
    l1_coefficient=8e-5,  # Sparsity penalty
    l1_warm_up_steps=1000,
    train_batch_size_tokens=4096,
    training_tokens=100_000_000,

    # Data
    dataset_path="monology/pile-uncopyrighted",
    context_size=128,

    # Logging
    log_to_wandb=True,
    wandb_project="sae-training",

    # Checkpointing
    checkpoint_path="checkpoints",
    n_checkpoints=5,
)

# 2. Train
trainer = SAETrainingRunner(cfg)
sae = trainer.run()

# 3. Evaluate
print(f"L0 (avg active features): {trainer.metrics['l0']}")
print(f"CE Loss Recovered: {trainer.metrics['ce_loss_score']}")

from transformer_lens import HookedTransformer
from sae_lens import SAE
import torch

model = HookedTransformer.from_pretrained("gpt2-small", device="cuda")
sae, _, _ = SAE.from_pretrained(
    release="gpt2-small-res-jb",
    sae_id="blocks.8.hook_resid_pre",
    device="cuda"
)

# Find what activates a specific feature
feature_idx = 1234
test_texts = [
    "The scientist conducted an experiment",
    "I love chocolate cake",
    "The code compiles successfully",
    "Paris is beautiful in spring",
]

for text in test_texts:
    tokens = model.to_tokens(text)
    _, cache = model.run_with_cache(tokens)
    features = sae.encode(cache["resid_pre", 8])
    activation = features[0, :, feature_idx].max().item()
    print(f"{activation:.3f}: {text}")

def steer_with_feature(model, sae, prompt, feature_idx, strength=5.0):
    """Add SAE feature direction to residual stream."""
    tokens = model.to_tokens(prompt)

    # Get feature direction from decoder
    feature_direction = sae.W_dec[feature_idx]  # [d_model]

    def steering_hook(activation, hook):
        # Add scaled feature direction at all positions
        activation += strength * feature_direction
        return activation

    # Generate with steering
    output = model.generate(
        tokens,
        max_new_tokens=50,
        fwd_hooks=[("blocks.8.hook_resid_pre", steering_hook)]
    )
    return model.to_string(output[0])

# Which features most affect a specific output?
tokens = model.to_tokens("The capital of France is")
_, cache = model.run_with_cache(tokens)

# Get features at final position
features = sae.encode(cache["resid_pre", 8])[0, -1]  # [d_sae]

# Get logit attribution per feature
# Feature contribution = feature_activation × decoder_weight × unembedding
W_dec = sae.W_dec  # [d_sae, d_model]
W_U = model.W_U    # [d_model, vocab]

# Contribution to "Paris" logit
paris_token = model.to_single_token(" Paris")
feature_contributions = features * (W_dec @ W_U[:, paris_token])

top_features = feature_contributions.topk(10)
print("Top features for 'Paris' prediction:")
for idx, val in zip(top_features.indices, top_features.values):
    print(f"  Feature {idx.item()}: {val.item():.3f}")

# WRONG: No warm-up, features die early
cfg = LanguageModelSAERunnerConfig(
    l1_coefficient=1e-4,
    l1_warm_up_steps=0,  # Bad!
)

# RIGHT: Warm-up L1 penalty
cfg = LanguageModelSAERunnerConfig(
    l1_coefficient=8e-5,
    l1_warm_up_steps=1000,  # Gradually increase
    use_ghost_grads=True,   # Revive dead features
)

# Reduce sparsity penalty
cfg = LanguageModelSAERunnerConfig(
    l1_coefficient=5e-5,  # Lower = better reconstruction
    d_sae=768 * 16,       # More capacity
)

# Increase sparsity (higher L1)
cfg = LanguageModelSAERunnerConfig(
    l1_coefficient=1e-4,  # Higher = sparser, more interpretable
)
# Or use TopK architecture
cfg = LanguageModelSAERunnerConfig(
    architecture="topk",
    activation_fn_kwargs={"k": 50},  # Exactly 50 active features
)

cfg = LanguageModelSAERunnerConfig(
    train_batch_size_tokens=2048,  # Reduce batch size
    store_batch_size_prompts=4,    # Fewer prompts in buffer
    n_batches_in_buffer=8,         # Smaller activation buffer
)