INDEX

Explanations

words related to Australia

oai_token-act-pair · gpt-3.5-turbo

the frequency of the substring "au" in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

é¾į

-0.71

ALLY

-0.65

appers

-0.65

eyes

-0.63

IONS

-0.62

selves

-0.61

orative

-0.61

 Cavaliers

-0.60

OB

-0.59

 selves

-0.59

POSITIVE LOGITS

gment

1.24

llah

1.22

ction

1.14

fman

1.06

pload

1.05

qua

1.01

cham

0.99

lette

0.96

vre

0.95

lly

0.94

Activations Density 0.041%

words related to Australia

the frequency of the substring "au" in the document

No Comments

No Known Activations