INDEX

Explanations

phrases related to poses a threat, danger, risk, or problem to various entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential threats or dangers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

essen

-0.74

endars

-0.73

 Manufact

-0.73

cknowled

-0.71

lang

-0.67

ynthesis

-0.66

 Celebr

-0.65

enson

-0.64

utenberg

-0.64

ciples

-0.64

POSITIVE LOGITS

 danger

1.41

 threat

1.37

 hazard

1.37

 risk

1.33

 risks

1.26

 dangers

1.22

 peril

1.18

 challenge

1.11

 disadvantage

1.09

threat

1.08

Activations Density 0.114%

phrases related to poses a threat, danger, risk, or problem to various entities

phrases indicating potential threats or dangers

No Comments

No Known Activations