Latent-Explorer is the Python implementation of the framework proposed in the paper "Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph".

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Multi-threaded scanner which identifies multiple RDP/VNC services

Causal Probing of a Bi-Encoder for Retrieval

Subprober is a powerful and efficient subdomain scanning tool written in Python. With the ability to handle large lists of subdomains. The tool offers concurrent scanning, allowing users to define their preferred concurrency level for faster results. Whether you are on Linux, Windows, or macos

A framework for evaluating auto-interp pipelines, i.e., natural language explanations of neurons.

Framework for probing tasks

Official repository for the paper: "Probing LLMs for Joint Encoding of Linguistic Categories." Findings of EMNLP 2023.

Probe and cluster antibody paratopes and clonotypes

The codebase for "DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models"

Repository with code for interpretability analyses of a recurrent neural network predicting German plural nouns.

Network probing tool crafted for datacenters (but not only)

Memory efficient convolution networks

The official code and dataset for EMNLP 2022 paper "COPEN: Probing Conceptual Knowledge in Pre-trained Language Models".

A framework for ASR probing using MDL approach

[NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

Probing Bert for part of speech (POS) and named entity recognition (NER) to alleviate the opacity of learned representations.

Code and data for the ACL 2022 paper "Probing as Quantifying Inductive Bias".

Probing for Predicate Argument Structures in Pretrained Language Models (ACL 2022).

[NAACL 2022 Findings]Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning