INDEX

Explanations

instances of the name "Jon"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

holders

-0.77

Constructed

-0.62

doors

-0.60

holder

-0.59

 IMAGES

-0.58

ragon

-0.57

sided

-0.57

 Workers

-0.56

spring

-0.56

Peb

-0.55

POSITIVE LOGITS

athon

1.37

ny

1.16

nie

1.08

atan

1.06

athan

1.01

Ben

1.01

Ã¡s

0.99

ason

0.94

kers

0.93

cheon

0.91

Activations Density 0.022%

instances of the name "Jon"

No Comments

No Known Activations