INDEX

Explanations

phrases related to step-by-step instructions or procedures

oai_token-act-pair · gpt-3.5-turbo

keywords and phrases related to food preparation and cooking methods

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

etheless

-0.67

"]=>

-0.66

ãĥ³ãĤ¸

-0.66

 risked

-0.65

quished

-0.64

 Shutterstock

-0.64

æ©

-0.62

é¾įå¥ĳå£«

-0.60

emouth

-0.60

 Wanted

-0.59

POSITIVE LOGITS

 finishes

1.36

 expires

1.28

 completes

1.26

 reaches

1.19

 ceases

1.09

 arrives

1.07

has

1.06

 clears

0.99

 concludes

0.97

 fades

0.95

Activations Density 0.283%

phrases related to step-by-step instructions or procedures

keywords and phrases related to food preparation and cooking methods

No Comments

No Known Activations