Tutorials#
![](../_static/images/tutorials/walkthrough.webp)
Walkthrough
Learn the basics
![](../_static/images/tutorials/activation_patching.webp)
Activation Patching
Causal intervention
![](../_static/images/tutorials/attribution_patching.webp)
Attribution Patching
Approximate patching
![](../_static/images/tutorials/logit_lens.webp)
Logit Lens
Decode activations
![](../_static/images/tutorials/future_lens.webp)
Future Lens
Probe future tokens
![](../_static/images/tutorials/function_vectors.webp)
Function Vectors
Lambdas
![](../_static/images/tutorials/dictionary_learning.webp)
Dictionary Learning
Sparse autoencoders
Boundless DAS
- Attribution Patching
- Setup (Ignore)
- 1️⃣ IOI Patching Setup
- 2️⃣ Attribution Patching Over Components
- 3️⃣ Attribution Patching Over Position
- Boundless DAS
- Setup (Ignore)
- Price Tagging game
- Prealign Task
- Boundless DAS
- Function Vectors
- Future Lens
- Activation Patching
- Logit Lens 🔎
- Setup (Ignore)
- GPT2 Model Architecture
- Dictionary Learning
- Walkthrough
- 1 First, let’s start small
- 2 Bigger
- 3 I thought you said huge models?
- Getting Involved!