Show HN: Ecco – See what your NLP language model is “thinking”
1–10 of 35 posts
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#2Hi HN,
Author here. I had been fascinated with Andrej Karpathy's article (https://karpathy.github.io/2015/05/21/rnn-effectiveness/) -- especially where it shows neurons being activated in response to brackets and indentation.
I built Ecco to enable examining neurons inside Transformer-based language models.
You can use Ecco to simply interact with a language model and see its output token by token(as it's built on the awesome Hugging Face transformers package). But more interestingly you can use it to examine neuron activations. The article explains more: https://jalammar.github.io/explaining-transformers/
I have a couple more visualizations I'd like to add in the future. It's open source, so feel free to help me improve it.
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#3looks great!
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#4looks great!
Thank you!
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#5Thank you, Jay! I appreciate the addition of the colab notebooks with code examples. I can't wait to play around with this and investigate how language models _speak_.
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#6Any examples of novel insights obtained with this method?
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#7Hi HN, Author here. I had been fascinated with Andrej Karpathy's article ( https://karpathy.github.io/2015/05/21/rnn-effectiveness/ ) -- especially where it shows neurons being activated in response to brackets and indentation. I built Ecco to enable examining neurons inside Transformer-based language models. You can use Ecco to simply interact with a language model and see its output token by token(as it's built on…
I can not thank you enough for your “The Illustrated Transformer” [1] that I have directed two cohorts of MSc students to – it is a true gem of an article. A few years ago my group made an interface to visualise contextual word representations [2] that looked like a primordial soup ancestor to your most recent article (no screenshots though, sadly). I hope putting these together brings you as much joy as it does to your fans in academia and education like myself reading it. Despite Chris Ohla’s effort with Distill, I still think we lack a good way to give the amount of credit efforts like yours deserve.
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#8Any examples of novel insights obtained with this method?
What I found most fascinating is identifying neuron firing patterns corresponding to linguistic properties: e.g. groups of neurons that fire in response to verbs, or pronounds.
Scroll down to "Factorizing Activations of a Single Layer" in https://jalammar.github.io/explaining-transformers/ to see those.
The figure above it, titled 'Explorable: Ten Activation Factors of XML' shows how neuron firing patterns in response to XML -- opening tags, closing tags, and even indentation.
It's still fresh, but I'm keen to see what other people uncover in their examinations (or what shortfalls/areas of improvement there are for such a method).
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#9Thank you, Jay! I appreciate the addition of the colab notebooks with code examples. I can't wait to play around with this and investigate how language models _speak_.
Thanks! Please let me know if you have any feedback!
Re: Show HN: Ecco – See what your NLP language model is “thinking”
#10Hi HN, Author here. I had been fascinated with Andrej Karpathy's article ( https://karpathy.github.io/2015/05/21/rnn-effectiveness/ ) -- especially where it shows neurons being activated in response to brackets and indentation. I built Ecco to enable examining neurons inside Transformer-based language models. You can use Ecco to simply interact with a language model and see its output token by token(as it's built on…
I can not thank you enough for your “The Illustrated Transformer” [1] that I have directed two cohorts of MSc students to – it is a true gem of an article. A few years ago my group made an interface to visualise contextual word representations [2] that looked like a primordial soup ancestor to your most recent article (no screenshots though, sadly). I hope putting these together brings you as much joy as it does to y…
I'd love to look at your group's visualizations! Is it a private repo? because the link doesn't open up. It never stops to blow my mind that we can represent words and concepts in vectors of numbers.
Thanks for your kind words! It's a labor of passion, honestly. And while in previous years it was a nights-and-weekends project, I have recently been giving it my entire time and focus -- which is why I'm able to dip my toes more heavily into R&D like Ecco and the "Explaining Transformers" article.