INDEX

Explanations

terms related to financial crimes, specifically money laundering

oai_token-act-pair · gpt-3.5-turbo

phrases related to money laundering

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yll

-0.81

cox

-0.73

ãĥĦ

-0.71

å£«

-0.71

birth

-0.71

Birth

-0.70

haw

-0.69

leigh

-0.69

chat

-0.69

ku

-0.69

POSITIVE LOGITS

aundering

1.42

 laundering

1.25

 laund

0.91

 trafficking

0.85

 receipts

0.80

 dealings

0.79

 offences

0.78

 scams

0.76

 cartels

0.76

aunder

0.75

Activations Density 0.022%

terms related to financial crimes, specifically money laundering

phrases related to money laundering

No Comments

No Known Activations