INDEX

Explanations

phrases related to actions or concepts involving changes or modifications

oai_token-act-pair · gpt-3.5-turbo

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

 Wage

-0.76

 Flavoring

-0.65

 Forward

-0.64

 Teacher

-0.64

ĸļ

-0.63

ilial

-0.63

uyomi

-0.62

 Ashe

-0.62

 Showdown

-0.62

 drawer

-0.60

POSITIVE LOGITS

 facto

1.31

arest

1.27

cember

1.23

 Blasio

1.22

activate

1.15

activated

1.13

vious

1.12

vel

1.09

utsche

1.05

jected

1.04

Activations Density 0.031%

phrases related to actions or concepts involving changes or modifications

No Comments

No Known Activations