INDEX

Explanations

mentions of being shot or shootings

oai_token-act-pair · gpt-3.5-turbo

references to shootings or instances of being shot

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

wcsstore

-0.91

DragonMagazine

-0.88

é¾įå¥ĳå£«

-0.78

ebook

-0.78

é£

-0.78

éĸ

-0.77

algia

-0.76

Else

-0.75

alg

-0.74

Foreign

-0.72

POSITIVE LOGITS

nikov

1.01

powder

0.99

 shot

0.88

shot

0.87

 bullets

0.83

gun

0.82

 fired

0.82

guns

0.78

 shots

0.77

 revolver

0.76

Activations Density 0.028%

mentions of being shot or shootings

references to shootings or instances of being shot

No Comments

No Known Activations