INDEX

Explanations

codes or technical terms such as "BS"

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

naire

-0.73

naires

-0.64

 Lauder

-0.62

igators

-0.62

ittal

-0.59

 Ceres

-0.58

 grave

-0.56

antly

-0.56

 Rooney

-0.55

 Spartans

-0.55

POSITIVE LOGITS

keley

0.94

wark

0.92

hirt

0.87

ãĥ©

0.85

wana

0.84

pedia

0.80

BIP

0.78

culosis

0.78

azaar

0.77

bles

0.75

Activations Density 0.102%

codes or technical terms such as "BS"

No Comments

No Known Activations