INDEX

Explanations

locations and dates

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

Mex

-1.16

 Romo

-1.13

Zap

-1.10

Mexico

-1.08

 Cowboys

-1.08

 Azerbai

-1.05

 Azerbaijan

-1.00

 Jagu

-1.00

 Mexicans

-1.00

 Mexican

-0.98

POSITIVE LOGITS

 Massachusetts

1.95

 Boston

1.89

Boston

1.84

 Worcester

1.70

 Lowell

1.63

 Suffolk

1.62

 Cambridge

1.49

achusetts

1.44

 Rhode

1.42

 Providence

1.40

Activations Density 0.237%

locations and dates

No Comments

No Known Activations