INDEX

Explanations

programming code snippets related to testing, assertions, and software development

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

 tremend

-1.22

senal

-1.14

bara

-1.06

iosyn

-1.02

chwitz

-0.97

ournal

-0.97

acca

-0.95

gee

-0.95

perty

-0.94

sterdam

-0.94

POSITIVE LOGITS

ruct

1.44

reet

1.40

alker

1.32

ream

1.30

anding

1.29

imating

1.27

imates

1.25

imated

1.18

imate

1.18

ophe

1.17

Activations Density 0.855%

programming code snippets related to testing, assertions, and software development

No Comments

No Known Activations