INDEX

Explanations

phrases related to religion and spirituality, especially those involving the concept of God

oai_token-act-pair · gpt-3.5-turbo

references to divine authority and religious concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sbm

-0.85

ockey

-0.81

 actionGroup

-0.78

imes

-0.75

rador

-0.74

amina

-0.74

Beer

-0.73

np

-0.71

inks

-0.71

neck

-0.70

POSITIVE LOGITS

 Almighty

1.11

 Himself

1.06

 redeemed

0.98

 Divinity

0.93

 Apostle

0.91

hovah

0.88

 Messiah

0.88

 Exodus

0.87

 deity

0.87

 apostle

0.86

Activations Density 0.062%

phrases related to religion and spirituality, especially those involving the concept of God

references to divine authority and religious concepts

No Comments

No Known Activations