INDEX

Explanations

phrases related to lists or series of items

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aped

-0.70

imates

-0.65

MpServer

-0.64

xual

-0.64

imation

-0.63

azeera

-0.56

ishi

-0.54

 advisory

-0.54

semb

-0.54

avid

-0.54

POSITIVE LOGITS

Secondly

2.43

 Secondly

2.40

 secondly

2.29

Second

2.20

 Second

2.06

second

1.90

 second

1.86

Next

1.28

 Next

1.18

 Then

1.18

Activations Density 0.211%

phrases related to lists or series of items

No Comments

No Known Activations