INDEX

Explanations

word or phrases related to political factions

oai_token-act-pair · gpt-3.5-turbo

references to political factions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zek

-0.68

realDonaldTrump

-0.67

ynthesis

-0.66

assetsadobe

-0.66

ipeg

-0.65

alm

-0.63

Bloomberg

-0.63

ynchronous

-0.61

odium

-0.61

Consumer

-0.60

POSITIVE LOGITS

naire

1.09

naires

1.01

 factions

0.91

 faction

0.89

 Faction

0.83

rons

0.75

 affili

0.74

 alliances

0.72

 vying

0.71

 members

0.71

Activations Density 0.022%

word or phrases related to political factions

references to political factions

No Comments

No Known Activations