INDEX

Explanations

proper nouns related to locations and names of people

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

flo

-0.72

undy

-0.71

 checks

-0.69

 cents

-0.68

 toys

-0.64

verson

-0.64

 jobs

-0.64

 reviews

-0.63

rpm

-0.63

reviewed

-0.63

POSITIVE LOGITS

Äĩ

1.25

oÄŁ

1.04

ÄŁ

1.02

 Municip

0.97

 Sheikh

0.93

 Yose

0.93

oglu

0.91

Vaj

0.89

Ã±o

0.89

rahim

0.88

Activations Density 0.723%

proper nouns related to locations and names of people

No Comments

No Known Activations