INDEX

Explanations

phrases related to communication and interpersonal interactions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tram

-0.70

mercial

-0.68

 commercial

-0.65

 psychiat

-0.64

 board

-0.64

 subsid

-0.62

 range

-0.62

 vulner

-0.61

 paved

-0.61

 aerial

-0.61

POSITIVE LOGITS

¹

1.38

ľ

1.33

ª

1.33

¡

1.27

Ķ

1.24

´

1.22

©

1.21

Ŀ

1.20

Ĳ

1.18

¦

1.18

Activations Density 0.126%

phrases related to communication and interpersonal interactions

No Comments

No Known Activations