INDEX

Explanations

terms related to criminal activities, specifically focusing on gangs

oai_token-act-pair · gpt-3.5-turbo

references to gang-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

OPLE

-0.81

etsk

-0.78

hower

-0.75

andum

-0.73

 concess

-0.70

*/(

-0.68

++++

-0.68

/+

-0.66

ibilities

-0.63

++++++++++++++++

-0.63

POSITIVE LOGITS

sta

1.29

busters

1.22

sters

1.17

ster

1.16

bang

1.12

rene

1.02

members

0.97

regate

0.92

buster

0.91

atown

0.87

Activations Density 0.028%

terms related to criminal activities, specifically focusing on gangs

references to gang-related activities

No Comments

No Known Activations