INDEX

Explanations

phrases related to posing risks or threats

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential threats or risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ciples

-0.74

 Manufact

-0.72

cknowled

-0.70

essen

-0.68

mith

-0.68

azines

-0.66

endars

-0.65

enson

-0.65

write

-0.65

£ı

-0.64

POSITIVE LOGITS

 threat

1.31

 hazard

1.27

 danger

1.20

 risk

1.15

 risks

1.07

 challenge

1.05

 dangers

1.02

 hazards

0.98

 hurdle

0.98

 peril

0.98

Activations Density 0.155%

phrases related to posing risks or threats

phrases indicating potential threats or risks

No Comments

No Known Activations