INDEX

Explanations

mentions of the word 'cat'

oai_token-act-pair · gpt-3.5-turbo

references to cats

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

htt

-0.71

gur

-0.67

 Vander

-0.65

 Glas

-0.64

 Sachs

-0.63

 Vaugh

-0.63

assetsadobe

-0.63

 Fellowship

-0.63

 rece

-0.62

demand

-0.62

POSITIVE LOGITS

aclysm

1.40

alogue

1.26

alog

1.16

apult

1.15

cat

1.10

hedral

1.08

heter

1.05

alyst

1.05

cher

1.00

chers

0.96

Activations Density 0.013%

mentions of the word 'cat'

references to cats

No Comments

No Known Activations