jalammar/ecco

Health v2 · maintenance only

Adoption not part of the score

2102 stars · 176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Ecco is a Python library for exploring and explaining Transformer-based NLP language models through interactive visualizations inside Jupyter notebooks. It supports feature attribution, neuron analysis, and model introspection for models like GPT2, BERT, RoBERTa, T5, and T0 via Hugging Face transformers.

Use cases

• visualize how a transformer language model processes text
• explain BERT or GPT-2 predictions with feature attribution
• inspect neuron activations in a language model
• understand attention and token importance in NLP models
• explore pre-trained Hugging Face models interactively in a notebook

When to choose

• you want interactive, notebook-based explanations of transformer model behavior
• you need saliency or integrated-gradients attributions for NLP predictions
• you are teaching or researching how language models work internally

When to avoid

• you need to train or fine-tune models - Ecco only explores pre-trained ones
• you need production model monitoring or dashboards outside Jupyter
• you need a stable, actively developed tool - it is an alpha research project

Facets

library · maturity maintenance

data-visualization nlp machine-learning data-visualization machine-learning developer-tools python jvm-scripting explainable-ai transformers jupyter-notebooks interpretability pytorch huggingface feature-attribution natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jalammar/ecco")