interp-reasoning / thought-anchorsLinks
⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
☆20Updated this week
Alternatives and similar repositories for thought-anchors
Users that are interested in thought-anchors are comparing it to the libraries listed below
Sorting:
- Induce brain-like topographic structure in your neural networks☆62Updated 2 weeks ago
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inf…☆24Updated 8 months ago
- pre-trained topographic models☆11Updated 3 months ago
- Repository to create traveling waves integrate special information through time☆53Updated 3 months ago
- ☆32Updated 3 weeks ago
- ☆13Updated 10 months ago
- ☆25Updated last month
- ☆21Updated 3 months ago
- BH hackathon☆14Updated last year
- ☆23Updated last month
- ☆11Updated last year
- ☆38Updated 11 months ago
- Portfolio REgret for Confidence SEquences☆20Updated 6 months ago
- ☆10Updated 2 months ago
- Understanding how features learned by neural networks evolve throughout training☆36Updated 8 months ago
- Repo for solving arc problems with an Neural Cellular Automata☆17Updated last month
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆19Updated 3 months ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆27Updated last month
- Latent Large Language Models☆18Updated 10 months ago
- Resa: Transparent Reasoning Models via SAEs☆36Updated 2 weeks ago
- Brain-like variational inference☆51Updated last month
- ☆31Updated last year
- The official evaluation suite and dynamic data release for MixEval.☆11Updated 9 months ago
- A tool to assist in the interpretation of learned features in sparse autoencoders (in particular the four SAE's trained by Joseph Bloom o…☆19Updated 8 months ago
- ARLC, a probabilistic abductive reasoner for solving Raven's progressive matrices.☆18Updated last month
- Collection of LLM completions for reasoning-gym task datasets☆24Updated last month
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated 11 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 3 months ago
- Lottery Ticket Adaptation☆39Updated 7 months ago
- ☆23Updated 6 months ago