INDEX

Explanations

phrases related to laws, policies, titles, or positions

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

 Tasman

-0.65

creen

-0.64

erous

-0.64

 Reprodu

-0.63

yip

-0.63

 Leilan

-0.62

eer

-0.62

 Catalyst

-0.61

 Laurent

-0.61

 Telephone

-0.60

POSITIVE LOGITS

Ĳ

1.44

ĳ

1.40

Ĵ

1.36

ł

1.30

ª

1.27

ı

1.25

ĸ

1.17

Ķ

1.12

ĵ

1.09

¹

1.09

Activations Density 0.109%

phrases related to laws, policies, titles, or positions

No Comments

No Known Activations