INDEX

Explanations

titles of TV shows and movies

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

sted

-0.49

otle

-0.49

".[

-0.45

ãĥĩ

-0.44

uine

-0.42

ãĢį

-0.42

ismo

-0.42

.ãĢį

-0.42

iasis

-0.41

 âĢİ

-0.41

POSITIVE LOGITS

 medial

0.43

 academ

0.41

ĨĴ

0.41

 collateral

0.40

 cran

0.40

reet

0.40

 spine

0.39

 cardinal

0.39

 Brist

0.39

 lineback

0.39

Activations Density 5.125%

titles of TV shows and movies

No Comments

No Known Activations