INDEX

Explanations

topics or situations that provoke strong reactions of anger or disapproval

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

wagen

-0.51

uchin

-0.50

ramer

-0.49

 Solitaire

-0.48

 counselor

-0.47

llan

-0.45

 cleaner

-0.45

ession

-0.44

kered

-0.44

properties

-0.44

POSITIVE LOGITS

ously

0.79

iously

0.74

 indignation

0.67

 uproar

0.58

 outcry

0.56

èĥ

0.53

 outrage

0.53

 loudly

0.52

ingly

0.50

storm

0.50

Activations Density 11.760%

topics or situations that provoke strong reactions of anger or disapproval

No Comments

No Known Activations