INDEX

Explanations

phrases related to vehicle operation and maintenance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zbek

-0.83

OTOS

-0.80

cffffcc

-0.78

raltar

-0.77

RN

-0.75

 Pist

-0.75

SH

-0.74

 nerv

-0.72

uters

-0.72

berman

-0.71

POSITIVE LOGITS

ainer

1.15

aint

1.14

luster

1.11

iffs

1.08

ained

1.06

aints

1.05

ifully

1.01

ickets

1.00

aining

0.99

iful

0.95

Activations Density 1.338%

phrases related to vehicle operation and maintenance

No Comments

No Known Activations