Skip to main content

TransformerLens Mechanistic Interpretability

Skill Verified Active

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Purpose

To enable researchers to deeply inspect and manipulate the internals of transformer models for understanding their learned algorithms and behavior.

Features

  • Inspect and manipulate transformer internals
  • Utilize HookPoints and activation caching
  • Perform activation patching and causal tracing
  • Analyze attention patterns and circuits
  • Support for 50+ transformer architectures

Use Cases

  • Reverse-engineering model algorithms
  • Studying attention patterns and information flow
  • Performing activation patching or causal tracing experiments
  • Analyzing specific circuits like induction heads

Non-Goals

  • Working with non-transformer architectures
  • Training or analyzing Sparse Autoencoders directly
  • Providing remote execution on massive models
  • Offering higher-level causal intervention abstractions

Practices

  • Model Interpretability
  • Transformer Analysis
  • Code Research

Prerequisites

  • Python >= 3.8
  • transformer-lens >= 2.0.0
  • torch >= 2.0.0

Trust

  • info:Issues AttentionOpen issues (90d): 17, Closed issues (90d): 4. The closure rate is low, indicating slower response times for open issues.

Installation

npx skills add davila7/claude-code-templates

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified
95 /100
Analyzed about 22 hours ago

Trust Signals

Last commitabout 24 hours ago
Stars27.2k
LicenseMIT
Status
View Source

Similar Extensions

Transformer Lens Interpretability

99

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Skill
Orchestra-Research

Embedding Strategies

100

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Skill
wshobson

Aws Cdk Development

100

AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.

Skill
zxkane

Fit Drift Diffusion Model

100

Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.

Skill
pjt222

Ui Ux Pro Max

100

UI/UX design intelligence with searchable style, palette, typography, and chart databases. Use when designing UI components, choosing colors/fonts, reviewing code for UX issues, building landing pages, or implementing responsive layouts.

Skill
spartan-stratos

Google Tts

100

Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".

Skill
sanjay3290

© 2025 SkillRepo · Find the right skill, skip the noise.