INDEX

Explanations

phrases related to making modifications or adjustments

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

BuyableInstoreAndOnline

-0.75

\":

-0.74

ĸļ

-0.71

interstitial

-0.66

Ħ¢

-0.64

awei

-0.62

ãĤ©

-0.62

ª

-0.59

æľ

-0.58

ocracy

-0.56

POSITIVE LOGITS

 depending

1.07

 anytime

0.99

 easily

0.94

 safely

0.88

 offline

0.86

 anonymously

0.84

 cheaply

0.83

 without

0.81

 anywhere

0.80

depending

0.80

Activations Density 1.063%

phrases related to making modifications or adjustments

No Comments

No Known Activations