Alternatives and similar repositories for trailtoken

Users that are interested in trailtoken are comparing it to the libraries listed below

• tech-srl / RASP
  An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"
  ☆315Updated 9 months ago
• i-machine-think / am-i-compositional
  ☆62Updated last year
• Kiv / fancy_einsum
  Einsum with einops style variable names
  ☆16Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆257Updated 6 months ago
• craffel / llm-seminar
  Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)
  ☆310Updated 2 years ago
• MilaNLProc / honest
  A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.
  ☆21Updated 2 months ago
• microsoft / adaptive-testing
  Find and fix bugs in natural language machine learning models using adaptive testing.
  ☆183Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆51Updated 3 years ago
• mega002 / lm-debugger
  The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.
  ☆177Updated 3 years ago
• ARBORproject / arborproject.github.io
  ☆77Updated 4 months ago
• CLARIN-PL / LEPISZCZE
  This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish
  ☆13Updated last year
• PAIR-code / interpretability
  PAIR.withgoogle.com and friend's work on interpretability methods
  ☆192Updated this week
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆265Updated last year
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆247Updated last year
• CLARIN-PL / embeddings
  Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polis…
  ☆36Updated last year
• EleutherAI / knowledge-neurons
  A library for finding knowledge neurons in pretrained transformer models.
  ☆158Updated 3 years ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆228Updated 5 months ago
• krishnap25 / mauve
  Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.
  ☆292Updated 11 months ago
• jannik-brinkmann / multilingual-features
  Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…
  ☆14Updated 2 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆207Updated 2 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆227Updated 8 months ago
• tpavlic / splncs04nat
  natbib compatible splncs04.bst (Springer LNCS) BibTeX Style File built using a docstrip with the conventional merlin.mbs master file.
  ☆51Updated 3 years ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆95Updated this week
• joshuacnf / paradox-learning2reason
  ☆34Updated 6 months ago
• microsoft / biosbias
  Code to reproduce data for Bias in Bios
  ☆46Updated 2 years ago
• allenai / mice
  ☆26Updated 2 years ago
• g8a9 / ferret
  A python package for benchmarking interpretability techniques on Transformers.
  ☆213Updated 8 months ago
• i-machine-think / diagNNose
  diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.
  ☆82Updated last year
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆68Updated 2 years ago