INDEX

Explanations

instances of the word "put" at various parts of the document

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "put."

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Nou

-0.68

 specialization

-0.63

externalActionCode

-0.57

 Heights

-0.57

 Integration

-0.56

 Flavoring

-0.56

 stripe

-0.55

 Magicka

-0.55

 Grounds

-0.55

 Assessment

-0.54

POSITIVE LOGITS

tering

1.30

tin

1.21

rid

1.18

atively

1.06

ative

1.06

downs

1.02

rescent

1.01

nam

1.00

ongh

0.99

 forth

0.96

Activations Density 0.040%

instances of the word "put" at various parts of the document

occurrences of the word "put."

No Comments

No Known Activations