INDEX

Explanations

text related to online scams, fraudulent activities, and illegal behaviors

oai_token-act-pair · gpt-3.5-turbo

references to scams and fraudulent activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.86

ĪĴ

-0.86

equal

-0.74

natureconservancy

-0.72

+++

-0.71

adj

-0.69

inguished

-0.69

Phys

-0.68

mosp

-0.66

eatures

-0.66

POSITIVE LOGITS

 extortion

1.33

 fraudulent

1.29

 scams

1.24

 traffickers

1.23

 ransom

1.22

 prostitutes

1.22

 bribes

1.21

 blackmail

1.21

 disgu

1.20

 unwitting

1.20

Activations Density 0.589%

text related to online scams, fraudulent activities, and illegal behaviors

references to scams and fraudulent activities

No Comments

No Known Activations