INDEX

Explanations

references to violent events involving shootings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "shot" in various contexts related to violence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.94

é¾įå¥ĳå£«

-0.82

Else

-0.79

wcsstore

-0.77

Econom

-0.73

Climate

-0.72

Future

-0.69

algia

-0.69

Space

-0.68

å¥³

-0.68

POSITIVE LOGITS

nikov

1.05

powder

1.00

gun

0.95

 wounds

0.87

guns

0.86

 dead

0.85

lessly

0.81

 rampage

0.80

 gunned

0.80

 unarmed

0.78

Activations Density 0.035%

references to violent events involving shootings

instances of the word "shot" in various contexts related to violence

No Comments

No Known Activations