INDEX

Explanations

words related to criminal activities

oai_token-act-pair · gpt-3.5-turbo

references to crime

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ersed

-0.79

achev

-0.78

por

-0.73

arity

-0.69

TPPStreamerBot

-0.68

uran

-0.68

zl

-0.66

Dak

-0.66

)=(

-0.66

paren

-0.65

POSITIVE LOGITS

 spree

1.09

 synd

0.84

fighting

0.81

 unfocusedRange

0.80

 offenses

0.80

 perpetrated

0.80

 punishable

0.80

fighter

0.78

 offences

0.78

 crimes

0.77

Activations Density 0.022%

words related to criminal activities

references to crime

No Comments

No Known Activations