Results for “transformerlens”

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.

• Exploring features in a pretrained SAE
• Training an SAE for a selected model layer
• Investigating inactive features and reconstruction errors

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.

The English summary is being prepared. Showing the original description.

Fornece orientação para pesquisa de interpretabilidade mecanística usando TransformerLens para inspecionar e manipular internals de transformers via HookPoints e caching de ativações. Use ao fazer engenharia reversa de algoritmos de modelos, estudar padrões de atenção ou realizar experimentos de activation patching.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Explore concepts learned by language models using sparse autoencoders, which separate internal activity into a small set of features. Analyze pretrained models, train custom autoencoders, assess reconstruction quality, and experiment with feature based output adjustments.

• Exploring features with a pretrained SAE
• Training an SAE for a chosen model layer
• Comparing feature responses across input texts

Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.

• Exploring features with a pretrained SAE
• Training and evaluating a custom SAE
• Studying overlapping concepts in model activity