Sign in

Ian Johnson 🔬🤖

@enjalot.bsky.social
327 followers 121 following 51 posts

Data Visualization and Machine Learning Building Latent Scope to visualize unstructured data through the lens of ML github.com/enjalot/latent-scope

PostsRepliesMedia
Ian Johnson 🔬🤖 @enjalot.bsky.social · 18/03/2025
mean pooling
120
Ian Johnson 🔬🤖 @enjalot.bsky.social · 23/01/2025
implemented a new rendering component for latent scope's scatter plot. had to replace regl-scatterplot with d3-zoom + regl shaders so we could support mobile
071
Reposted by Ian Johnson 🔬🤖
dribnet @drib.net · 11/12/2024
I'll be at @unireps.bsky.social this Saturday presenting a new experimental pipeline to visually explore structured neural network representations. The core idea is to take thousands of prompts that activate a concept, and then cluster and draw them using MultiDiffusion. 🧵👇
2318
Ian Johnson 🔬🤖 @enjalot.bsky.social · 10/12/2024
am i missing something for handling image data in parquet files? I can load a dataset from HF like: dataset = load_dataset("Marqo/marqo-ge-sample", split='google_shopping') df = pd.DataFrame(dataset) but i need to convert the images to bytes if I want to do: df.to_parquet("sample.parquet")
120
Reposted by Ian Johnson 🔬🤖
Alexander Doria @dorialexander.bsky.social · 05/12/2024
“They said it could not be done”. We’re releasing Pleias 1.0, the first suite of models trained on open data (either permissibly licensed or uncopyrighted): Pleias-3b, Pleias-1b and Pleias-350m, all based on the two trillion tokens set from Common Corpus.
924884
Reposted by Ian Johnson 🔬🤖
Lynn Cherny @arnicas.bsky.social · 05/12/2024
CLIP search for 562K maps in Lib of Congress github.com/j-mahowald/c... Paper: 2024.computational-humanities-research.org/papers/paper... #chr2024
github.com
GitHub - j-mahowald/clip-loc-maps: Repository for the paper "Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIP"
Repository for the paper "Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIP" - j-mahowald/clip-loc-maps
1265
Ian Johnson 🔬🤖 @enjalot.bsky.social · 05/12/2024
the algorithm is not some deity but a landscape, the feed is an uber ride across the manifold, only the windows are blacked out. what if you had a map of the algorithm? what if the UX of the feed let you look out of the window? musing with @infowetrust.com image from distill.pub/2017/aia/
053
Reposted by Ian Johnson 🔬🤖
Duarte @duarteocarmo.com · 03/12/2024
Spent the day playing with this. I'm absolutely blown away @enjalot.bsky.social! - Chose any embedding from HF - Project with UMAP, cluster with HDBSCAN - Use Ollama to label the clusters (Works incredibly well!)
enjalot.github.io
Latent Scope
082
Ian Johnson 🔬🤖 @enjalot.bsky.social · 03/12/2024
😙👌📊📈📚
020
Ian Johnson 🔬🤖 @enjalot.bsky.social · 29/11/2024
what's crazy to me is that so many of these can be run very efficiently on an M1 MacBook pro, and just fine on a VM with only CPU. crazy how much value you can pull out of text without billions of parameters
060
Reposted by Ian Johnson 🔬🤖
Tom Aarsen @tomaarsen.com · 29/11/2024
If you're interested in embedding models for retrieval (search), clustering, classification, paraphrase mining, etc., then there's now 10,000 fully free and open source options on @hf.co via Sentence Transformers. Check out the most popular ones here: huggingface.co/models?libra...
2327
Ian Johnson 🔬🤖 @enjalot.bsky.social · 26/11/2024
Hidden States is happening next week in SF! It's a one-day unconference gathering researchers, designers, prototypers and engineers interested in pushing the boundaries of AI interfaces, going below the API and working with the hidden states. hiddenstates.org
1122
Ian Johnson 🔬🤖 @enjalot.bsky.social · 21/11/2024
One way I've been thinking about ML models for some time is as a lens. The weights are crystalized patterns whose structure emerges from the crushing pressures of backpropagation. By shining a piece of data through this lens you see the patterns diffracted in the hidden states.
2102
Ian Johnson 🔬🤖 @enjalot.bsky.social · 15/11/2024
allow me to reintroduce myself! I'm a prototyper and Data Alchemist interested in using machine learning for data visualization. I'm building github.com/enjalot/late... using the lessons learned from co-authoring these 4 distill.pub papers
2172
Ian Johnson 🔬🤖 @enjalot.bsky.social · 13/11/2024
I'm here now! excited to meet up with folks in SF on Dec 3rd
042
Reposted by Ian Johnson 🔬🤖
Lynn Cherny @arnicas.bsky.social · 07/11/2024
Posting for Ian Johnson from other place - unconf Dec 3 in San Fran on embeddings/SAE etc hiddenstates.org
hiddenstates.org
073
Ian Johnson 🔬🤖 @enjalot.bsky.social · 13/11/2024
👋
020