Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Pyvene Interventions

Skill Verifiziert Aktiv

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.

Zweck

To enable researchers and developers to perform reproducible causal interventions on PyTorch models, test hypotheses about model behavior, and understand model components.

Funktionen

  • Declarative intervention framework
  • Support for activation patching and causal tracing
  • Interchange Intervention Training (IIT)
  • Saving and sharing interventions via HuggingFace
  • Compatibility with any PyTorch model

Anwendungsfälle

  • Testing causal hypotheses about model components
  • Reproducing and sharing intervention experiments
  • Conducting ROME-style causal tracing
  • Performing activation patching for circuit analysis

Nicht-Ziele

  • Exploratory activation analysis (use TransformerLens)
  • Training/analyzing SAEs (use SAELens)
  • Remote execution on massive models (use nnsight)
  • Lower-level control than pyvene offers (use nnsight)

Trust

  • info:Issues AttentionThere are 17 open issues and 4 closed issues in the last 90 days, indicating a closure rate below 50% and a moderate level of engagement.

Installation

npx skills add davila7/claude-code-templates

Führt das Vercel skills CLI (skills.sh) via npx aus — benötigt Node.js lokal und mindestens einen installierten skills-kompatiblen Agent (Claude Code, Cursor, Codex, …). Setzt voraus, dass das Repo dem agentskills.io-Format folgt.

Qualitätspunktzahl

Verifiziert
96 /100
Analysiert 1 day ago

Vertrauenssignale

Letzter Commit1 day ago
Sterne27.2k
LizenzMIT
Status
Quellcode ansehen

Ähnliche Erweiterungen

Pyvene Causal Interventions

97

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.

Skill
Orchestra-Research

Nnsight Remote Interpretability

99

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Skill
davila7

PyTorch Lightning

100

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Skill
K-Dense-AI

TimesFM Forecasting

100

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Skill
K-Dense-AI

SHAP Model Interpretability

100

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Skill
K-Dense-AI

Implementing Llms Litgpt

100

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Skill
davila7