跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

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.

Orchestra Research · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add Orchestra-Research/AI-Research-SKILLs --skill pyvene-interventions

技能说明


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]

pyvene: Causal Interventions for Neural Networks

pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.

GitHub: stanfordnlp/pyvene (840+ stars) Paper: pyvene: A Library for Understanding and Improving PyTorch Models via Interventions (NAACL 2024)

When to Use pyvene

Use pyvene when you need to:

  • Perform causal tracing (ROME-style localization)
  • Run activation patching experiments
  • Conduct interchange intervention training (IIT)
  • Test causal hypotheses about model components
  • Share/reproduce intervention experiments via HuggingFace
  • Work with any PyTorch architecture (not just transformers)

Consider alternatives when:

  • You need exploratory activation analysis → Use TransformerLens
  • You want to train/analyze SAEs → Use SAELens
  • You need remote execution on massive models → Use nnsight
  • You want lower-level control → Use nnsight

Installation

pip install pyvene

Standard import:

import pyvene as pv

Core Concepts

IntervenableModel

The main class that wraps any PyTorch model with intervention capabilities:

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)

Intervention Types

TypeDescriptionUse Case
VanillaInterventionSwap activations between runsActivation patching
AdditionInterventionAdd activations to base runSteering, ablation
SubtractionInterventionSubtract activationsAblation
ZeroInterventionZero out activationsComponent knockout
RotatedSpaceInterventionDAS trainable interventionCausal discovery
CollectInterventionCollect activationsProbing, analysis

Component Targets

# 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
]

Workflow 1: Causal Tracing (ROME-style)

Locate where factual associations are stored by corrupting inputs and restoring activations.

Step-by-Step

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

Checklist

  • Prepare clean prompt with target factual association
  • Create corrupted version (noise or counterfactual)
  • Define intervention co
阅读完整来源 ↗