INDEX

Explanations

phrases related to numbers and quantities

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

 Wilde

-0.70

tips

-0.64

 eased

-0.58

 Journalism

-0.55

RHP

-0.55

VD

-0.53

 Hague

-0.52

 Freeman

-0.52

 Marty

-0.52

 Padres

-0.52

POSITIVE LOGITS

multiple

1.32

 multiple

1.23

Multiple

1.20

 Multiple

1.10

ãĥ¯ãĥ³

1.07

 simultaneously

1.07

 consecut

1.05

 totality

0.99

ultane

0.93

 simultaneous

0.93

Activations Density 1.270%

phrases related to numbers and quantities

No Comments

No Known Activations