INDEX

Explanations

ancient and historical names or terms with unusual characters or spellings

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

heed

-0.88

¥µ

-0.86

 rall

-0.84

 Amos

-0.80

pled

-0.79

 modem

-0.75

ctica

-0.73

 Bots

-0.73

coni

-0.72

cible

-0.72

POSITIVE LOGITS

keye

1.23

icago

1.15

rome

1.07

annel

1.06

ynski

1.04

otomy

1.03

sen

0.99

onne

0.99

ards

0.98

oly

0.98

Activations Density 6.532%

ancient and historical names or terms with unusual characters or spellings

No Comments

No Known Activations