Alternatives and similar repositories for SAE-Ravel

Users that are interested in SAE-Ravel are comparing it to the libraries listed below

• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆47Updated 7 months ago
• tatsu-lab / linguistic_calibration
  Align your LM to express calibrated verbal statements of confidence in its long-form generations.
  ☆25Updated 11 months ago
• milesaturpin / cot-unfaithfulness
  ☆44Updated last year
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆58Updated 6 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆74Updated 3 weeks ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• declare-lab / resta
  Restore safety in fine-tuned language models through task arithmetic
  ☆28Updated last year
• jiahai-feng / binding-iclr
  ☆14Updated last year
• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]
  ☆30Updated 4 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆89Updated last week
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆34Updated last year
• ruiqi-zhong / nlparam
  Augmenting Statistical Models with Natural Language Parameters
  ☆26Updated 8 months ago
• hannamw / EAP-IG
  ☆34Updated 2 weeks ago
• javiferran / sae_entities
  ☆36Updated 2 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆56Updated last year
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 2 months ago
• allenai / hyper-task-descriptions
  Learning adapter weights from task descriptions
  ☆18Updated last year
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆39Updated 4 months ago
• princeton-nlp / Edge-Pruning
  [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
  ☆56Updated 2 months ago
• yihuaihong / ConceptVectors
  ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆35Updated 3 months ago
• balevinstein / Probes
  ☆50Updated last year
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆35Updated 6 months ago
• tim-lawson / mlsae
  Multi-Layer Sparse Autoencoders (ICLR 2025)
  ☆23Updated 3 months ago
• y0mingzhang / diffuse-distributions
  Forcing Diffuse Distributions out of Language Models
  ☆15Updated 8 months ago
• McGill-NLP / AdversarialTriggers
  Code for "Universal Adversarial Triggers Are Not Universal."
  ☆17Updated last year
• locuslab / acr-memorization
  ☆34Updated 5 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• saprmarks / geometry-of-truth
  ☆83Updated 9 months ago