INDEX

Explanations

linguistic patterns or phrases associated with religious or spiritual practices, particularly focusing on linga symbolism

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ramid

-0.99

athetic

-0.99

ructose

-0.98

owitz

-0.97

paio

-0.96

hemat

-0.95

endix

-0.93

zyk

-0.93

alon

-0.93

athy

-0.92

POSITIVE LOGITS

 memories

1.03

 ling

1.02

 impressions

1.00

 Memories

0.98

wip

0.98

 Ling

0.97

uated

0.97

estate

0.95

uation

0.93

ently

0.92

Activations Density 1.559%

linguistic patterns or phrases associated with religious or spiritual practices, particularly focusing on linga symbolism

No Comments

No Known Activations