INDEX

Explanations

mentions of medical terms and fictional elements like monsters or magical creatures

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

Pru

-0.94

 conflic

-0.88

 behavi

-0.88

 warr

-0.83

 exha

-0.83

 captcha

-0.82

 cannabin

-0.82

 citiz

-0.81

 antioxid

-0.78

rongh

-0.78

POSITIVE LOGITS

avier

1.28

posed

1.26

press

1.24

imity

1.23

actly

1.23

aminer

1.22

odus

1.19

posure

1.16

ample

1.16

ternal

1.10

Activations Density 12.909%

mentions of medical terms and fictional elements like monsters or magical creatures

No Comments

No Known Activations