Type: AI model or model family
Pythia-160m appears in the radar stream as a model or model family. This page is a living index of dated mentions and sources — open Recent Updates and Backlinks for context, not a full product brief.
Recent Updates
- 2026-06-19: Paper measures how linear trained transformer FFN blocks actually are (cs.CL updates on arXiv.org) · arxiv.org — arXiv · alphaXiv · CatalyzeX · DagsHub · Hugging Face · scite · Litmaps · CORE · IArxiv · ScienceCast · GPT-2 · llama-160m
- 2026-06-19: How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural (cs.LG updates on arXiv.org) · arxiv.org — LLM Evals GPT-2 · llama-160m
- 2026-07-03: Expander Sparse Autoencoders propose a parameter-efficient SAE decoder (cs.LG updates on arXiv.org) · arxiv.org — arXiv Rodrigo Mendoza Smith · Pythia 70M · Qwen2.5-3B · Llama-3.2-1B
- 2026-07-08: No Subspace to Track: a paper argues low-rank optimizer subspaces are noisy and non-identifiable (cs.LG updates on arXiv.org) · arxiv.org
- 2026-07-29: Towards Robust Reinforcement Learning for Small-Scale Language Model Agents (cs.AI updates on arXiv.org) · arxiv.org — Agents Md Rezwanul Haque Pythia 70M Pythia 410M · SmolLM2-135M SmolLM2 360M
FAQ
What is Pythia-160m?
Pythia-160m appears in the radar stream as a model or model family. This page is a living index of dated mentions and sources — open Recent Updates and Backlinks for context, not a full product brief.
What does this page track?
Dated radar mentions, source links, related concepts, and builder-relevant context for Pythia-160m, collected automatically by GROUNDING.
When was Pythia-160m last mentioned?
Pythia-160m was most recently mentioned in a radar update dated 2026-07-29.
Category: Text / Language Models