INDEX

Explanations

technical terms and expressions related to legal matters or investigative processes

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

interrupted

-0.86

cake

-0.81

SHIP

-0.79

uates

-0.76

enance

-0.73

iates

-0.72

ians

-0.71

ENTS

-0.71

 Kush

-0.70

rition

-0.70

POSITIVE LOGITS

azy

1.12

igh

1.09

asure

1.05

uth

1.00

avement

0.99

pload

0.98

ppings

0.98

eker

0.97

ivably

0.96

vered

0.95

Activations Density 6.882%

technical terms and expressions related to legal matters or investigative processes

No Comments

No Known Activations