INDEX

Explanations

phrases related to prohibitions and bans

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

ensional

-0.48

ricia

-0.43

stals

-0.42

framework

-0.41

larg

-0.41

engine

-0.41

eline

-0.40

heric

-0.40

mund

-0.40

mint

-0.39

POSITIVE LOGITS

BuyableInstoreAndOnline

0.45

 discriminating

0.44

 interfering

0.42

 Cruel

0.41

 Cosmetic

0.40

 Parenthood

0.40

 Brune

0.40

 indefinitely

0.40

 airspace

0.39

 cruel

0.39

Activations Density 22.310%

phrases related to prohibitions and bans

No Comments

No Known Activations