INDEX

Explanations

commands or requests prompting action

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

catentry

-0.37

 anterior

-0.34

Introduced

-0.34

immune

-0.34

ection

-0.33

henko

-0.33

 inherent

-0.33

 opting

-0.32

 Breed

-0.32

 compounded

-0.31

POSITIVE LOGITS

Ô

0.36

achu

0.34

 Hobbit

0.33

 Rica

0.33

stown

0.33

resents

0.33

Wiz

0.32

 laun

0.32

acht

0.31

Champ

0.31

Activations Density 11.554%

commands or requests prompting action

No Comments

No Known Activations

commands or requests prompting action

No Comments

No Known Activations