INDEX

Explanations

phrases related to heated discussions or arguments

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

ulhu

-0.66

opathy

-0.65

abetic

-0.64

ateral

-0.63

adr

-0.61

idas

-0.59

allows

-0.57

graded

-0.56

ipt

-0.56

ramid

-0.55

POSITIVE LOGITS

ly

0.85

 applause

0.70

 heated

0.70

 discussion

0.67

 debates

0.66

 discussions

0.65

 debate

0.64

 uproar

0.64

 conversation

0.61

 exchanges

0.60

Activations Density 12.324%

phrases related to heated discussions or arguments

No Comments

No Known Activations