INDEX

Explanations

prefixes and suffixes in text

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

neau

-0.51

velt

-0.48

caster

-0.47

istic

-0.46

anship

-0.46

iste

-0.45

arist

-0.45

istically

-0.45

ischer

-0.44

anova

-0.44

POSITIVE LOGITS

enhagen

0.46

-+

0.42

-+-+-+-+

0.41

ãĥ¼ãĥĨãĤ£

0.41

entimes

0.41

 cumbers

0.40

 Centauri

0.40

 prefix

0.40

 subst

0.39

esville

0.39

Activations Density 0.176%

prefixes and suffixes in text

No Comments

No Known Activations