INDEX

Explanations

terms related to terrorism, terrorist threats, and extremist groups

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dit

-0.79

Cth

-0.70

 Myster

-0.68

 Vaugh

-0.67

yards

-0.66

ups

-0.65

 Goose

-0.65

 Quadro

-0.65

alky

-0.65

 Minotaur

-0.64

POSITIVE LOGITS

abad

1.31

iyah

0.99

istani

0.98

ophobic

0.97

Ø±

0.92

Islam

0.90

 Hussain

0.89

Islamic

0.89

hammad

0.88

 cleric

0.88

Activations Density 2.298%

terms related to terrorism, terrorist threats, and extremist groups

No Comments

No Known Activations