INDEX

Explanations

references and mentions of the news network CNN

oai_token-act-pair · gpt-3.5-turbo

references to the news network CNN

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

phant

-0.76

hot

-0.69

ocene

-0.68

cold

-0.66

vol

-0.66

plates

-0.66

FUL

-0.65

mits

-0.64

gging

-0.64

laus

-0.62

POSITIVE LOGITS

Money

0.95

 affiliate

0.93

CNN

0.89

ileaks

0.83

ienne

0.83

CNN

0.80

ial

0.75

pedia

0.75

ILLE

0.75

iliate

0.73

Activations Density 0.010%

references and mentions of the news network CNN

references to the news network CNN

No Comments

No Known Activations