pyvene-interventions

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

インストールへ移動

リポジトリ: davila7/claude-code-templates
ソースの最終更新活動: 2026年1月8日 14:24
検出された SKILL.md の言語: 英語
スター: 30,229
フォーク: 3,394

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。

npx skills add https://github.com/davila7/claude-code-templates --skill pyvene-interventions

コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。

ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

ファイルエクスプローラー

4 ファイル

SKILL.md

ソースの指示 · 読み取り専用プレビュー

検索に戻るインストールに戻る

pip install pyvene

import pyvene as pv

import pyvene as pv
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model
model = AutoModelForCausalLM.from_pretrained("gpt2")
tokenizer = AutoTokenizer.from_pretrained("gpt2")

# Define intervention configuration
config = pv.IntervenableConfig(
    representations=[
        pv.RepresentationConfig(
            layer=8,
            component="block_output",
            intervention_type=pv.VanillaIntervention,
        )
    ]
)

# Create intervenable model
intervenable = pv.IntervenableModel(config, model)

Type	Description	Use Case
`VanillaIntervention`	Swap activations between runs	Activation patching
`AdditionIntervention`	Add activations to base run	Steering, ablation
`SubtractionIntervention`	Subtract activations	Ablation
`ZeroIntervention`	Zero out activations	Component knockout
`RotatedSpaceIntervention`	DAS trainable intervention	Causal discovery
`CollectIntervention`	Collect activations	Probing, analysis

# Available components to intervene on
components = [
    "block_input",      # Input to transformer block
    "block_output",     # Output of transformer block
    "mlp_input",        # Input to MLP
    "mlp_output",       # Output of MLP
    "mlp_activation",   # MLP hidden activations
    "attention_input",  # Input to attention
    "attention_output", # Output of attention
    "attention_value_output",  # Attention value vectors
    "query_output",     # Query vectors
    "key_output",       # Key vectors
    "value_output",     # Value vectors
    "head_attention_value_output",  # Per-head values
]

import pyvene as pv
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("gpt2-xl")
tokenizer = AutoTokenizer.from_pretrained("gpt2-xl")

# 1. Define clean and corrupted inputs
clean_prompt = "The Space Needle is in downtown"
corrupted_prompt = "The ##### ###### ## ## ########"  # Noise

clean_tokens = tokenizer(clean_prompt, return_tensors="pt")
corrupted_tokens = tokenizer(corrupted_prompt, return_tensors="pt")

# 2. Get clean activations (source)
with torch.no_grad():
    clean_outputs = model(**clean_tokens, output_hidden_states=True)
    clean_states = clean_outputs.hidden_states

# 3. Define restoration intervention
def run_causal_trace(layer, position):
    """Restore clean activation at specific layer and position."""
    config = pv.IntervenableConfig(
        representations=[
            pv.RepresentationConfig(
                layer=layer,
                component="block_output",
                intervention_type=pv.VanillaIntervention,
                unit="pos",
                max_number_of_units=1,
            )
        ]
    )

    intervenable = pv.IntervenableModel(config, model)

    # Run with intervention
    _, patched_outputs = intervenable(
        base=corrupted_tokens,
        sources=[clean_tokens],
        unit_locations={"sources->base": ([[[position]]], [[[position]]])},
        output_original_output=True,
    )

    # Return probability of correct token
    probs = torch.softmax(patched_outputs.logits[0, -1], dim=-1)
    seattle_token = tokenizer.encode(" Seattle")[0]
    return probs[seattle_token].item()

# 4. Sweep over layers and positions
n_layers = model.config.n_layer
seq_len = clean_tokens["input_ids"].shape[1]

results = torch.zeros(n_layers, seq_len)
for layer in range(n_layers):
    for pos in range(seq_len):
        results[layer, pos] = run_causal_trace(layer, pos)

# 5. Visualize (layer x position heatmap)
# High values indicate causal importance

import pyvene as pv
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("gpt2")
tokenizer = AutoTokenizer.from_pretrained("gpt2")

# IOI task setup
clean_prompt = "When John and Mary went to the store, Mary gave a bottle to"
corrupted_prompt = "When John and Mary went to the store, John gave a bottle to"

clean_tokens = tokenizer(clean_prompt, return_tensors="pt")
corrupted_tokens = tokenizer(corrupted_prompt, return_tensors="pt")

john_token = tokenizer.encode(" John")[0]
mary_token = tokenizer.encode(" Mary")[0]

def logit_diff(logits):
    """IO - S logit difference."""
    return logits[0, -1, john_token] - logits[0, -1, mary_token]

# Patch attention output at each layer
def patch_attention(layer):
    config = pv.IntervenableConfig(
        representations=[
            pv.RepresentationConfig(
                layer=layer,
                component="attention_output",
                intervention_type=pv.VanillaIntervention,
            )
        ]
    )

    intervenable = pv.IntervenableModel(config, model)

    _, patched_outputs = intervenable(
        base=corrupted_tokens,
        sources=[clean_tokens],
    )

    return logit_diff(patched_outputs.logits).item()

# Find which layers matter
results = []
for layer in range(model.config.n_layer):
    diff = patch_attention(layer)
    results.append(diff)
    print(f"Layer {layer}: logit diff = {diff:.3f}")

import pyvene as pv
from transformers import AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained("gpt2")

# 1. Define trainable intervention
config = pv.IntervenableConfig(
    representations=[
        pv.RepresentationConfig(
            layer=6,
            component="block_output",
            intervention_type=pv.RotatedSpaceIntervention,  # Trainable
            low_rank_dimension=64,  # Learn 64-dim subspace
        )
    ]
)

intervenable = pv.IntervenableModel(config, model)

# 2. Set up training
optimizer = torch.optim.Adam(
    intervenable.get_trainable_parameters(),
    lr=1e-4
)

# 3. Training loop (simplified)
for base_input, source_input, target_output in dataloader:
    optimizer.zero_grad()

    _, outputs = intervenable(
        base=base_input,
        sources=[source_input],
    )

    loss = criterion(outputs.logits, target_output)
    loss.backward()
    optimizer.step()

# 4. Analyze learned intervention
# The rotation matrix reveals causal subspace
rotation = intervenable.interventions["layer.6.block_output"][0].rotate_layer

# Low-rank rotation finds interpretable subspaces
config = pv.IntervenableConfig(
    representations=[
        pv.RepresentationConfig(
            layer=8,
            component="block_output",
            intervention_type=pv.LowRankRotatedSpaceIntervention,
            low_rank_dimension=1,  # Find 1D causal direction
        )
    ]
)

import pyvene as pv
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")

# Load pre-trained steering intervention
intervenable = pv.IntervenableModel.load(
    "zhengxuanzenwu/intervenable_honest_llama2_chat_7B",
    model=model,
)

# Generate with steering
prompt = "Is the earth flat?"
inputs = tokenizer(prompt, return_tensors="pt")

# Intervention applied during generation
outputs = intervenable.generate(
    inputs,
    max_new_tokens=100,
    do_sample=False,
)

print(tokenizer.decode(outputs[0]))

# Save locally
intervenable.save("./my_intervention")

# Load from local
intervenable = pv.IntervenableModel.load(
    "./my_intervention",
    model=model,
)

# Share on HuggingFace
intervenable.save_intervention("username/my-intervention")

# Load from HuggingFace
intervenable = pv.IntervenableModel.load(
    "username/my-intervention",
    model=model,
)

# WRONG: Incorrect component name
config = pv.RepresentationConfig(
    component="mlp",  # Not valid!
)

# RIGHT: Use exact component name
config = pv.RepresentationConfig(
    component="mlp_output",  # Valid
)

# Ensure source and base have compatible shapes
# For position-specific interventions:
config = pv.RepresentationConfig(
    unit="pos",
    max_number_of_units=1,  # Intervene on single position
)

# Specify locations explicitly
intervenable(
    base=base_tokens,
    sources=[source_tokens],
    unit_locations={"sources->base": ([[[5]]], [[[5]]])},  # Position 5
)

# Use gradient checkpointing
model.gradient_checkpointing_enable()

# Or intervene on fewer components
config = pv.IntervenableConfig(
    representations=[
        pv.RepresentationConfig(
            layer=8,  # Single layer instead of all
            component="block_output",
        )
    ]
)

# pyvene v0.1.8+ supports LoRAs as interventions
config = pv.RepresentationConfig(
    intervention_type=pv.LoRAIntervention,
    low_rank_dimension=16,
)

Class	Purpose
`IntervenableModel`	Main wrapper for interventions
`IntervenableConfig`	Configuration container
`RepresentationConfig`	Single intervention specification
`VanillaIntervention`	Activation swapping
`RotatedSpaceIntervention`	Trainable DAS intervention
`CollectIntervention`	Activation collection

File	Contents
references/README.md	Overview and quick start guide
references/api.md	Complete API reference for IntervenableModel, intervention types, configurations
references/tutorials.md	Step-by-step tutorials for causal tracing, activation patching, DAS

name	pyvene-interventions
description	Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
version	1.0.0
author	Orchestra Research
license	MIT
tags	["Causal Intervention","pyvene","Activation Patching","Causal Tracing","Interpretability"]
dependencies	["pyvene>=0.1.8","torch>=2.0.0","transformers>=4.30.0"]

name	pyvene-interventions
description	Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
version	1.0.0
author	Orchestra Research
license	MIT
tags	["Causal Intervention","pyvene","Activation Patching","Causal Tracing","Interpretability"]
dependencies	["pyvene>=0.1.8","torch>=2.0.0","transformers>=4.30.0"]

Feature	pyvene	TransformerLens	nnsight
Declarative config	Yes	No	No
HuggingFace sharing	Yes	No	No
Trainable interventions	Yes	Limited	Yes
Any PyTorch model	Yes	Transformers only	Yes
Remote execution	No	No	Yes (NDIF)

pyvene-interventions

インストール方法

ソースファイルを確認

pyvene: Causal Interventions for Neural Networks

pyvene: Causal Interventions for Neural Networks

When to Use pyvene

Installation

Core Concepts

IntervenableModel

Intervention Types

Component Targets

Workflow 1: Causal Tracing (ROME-style)

Step-by-Step

Checklist

Workflow 2: Activation Patching for Circuit Analysis

Step-by-Step

Workflow 3: Interchange Intervention Training (IIT)

Step-by-Step

DAS (Distributed Alignment Search)

Workflow 4: Model Steering (Honest LLaMA)

Saving and Sharing Interventions

Common Issues & Solutions

Issue: Wrong intervention location

Issue: Dimension mismatch

Issue: Memory with large models

Issue: LoRA integration

Key Classes Reference

Supported Models

Reference Documentation

External Resources

Tutorials

Papers

Official Documentation

Comparison with Other Tools

pyvene-interventions

ソース情報

インストール方法

ソースファイルを確認

このリポジトリの他の Skills

このリポジトリの他の Skills

pyvene: Causal Interventions for Neural Networks

pyvene: Causal Interventions for Neural Networks

When to Use pyvene

Installation

Core Concepts

IntervenableModel

Intervention Types

Component Targets

Workflow 1: Causal Tracing (ROME-style)

Step-by-Step

Checklist

Workflow 2: Activation Patching for Circuit Analysis

Step-by-Step

Workflow 3: Interchange Intervention Training (IIT)

Step-by-Step

DAS (Distributed Alignment Search)

Workflow 4: Model Steering (Honest LLaMA)

Saving and Sharing Interventions

Common Issues & Solutions

Issue: Wrong intervention location

Issue: Dimension mismatch

Issue: Memory with large models

Issue: LoRA integration

Key Classes Reference

Supported Models

Reference Documentation

External Resources

Tutorials

Papers

Official Documentation

Comparison with Other Tools