INDEX

Explanations

detailed numerical data, including measurements, percentages, and specific values

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

lehem

-0.83

erity

-0.83

blance

-0.76

cerning

-0.73

å¥³

-0.70

Ü

-0.68

DragonMagazine

-0.68

soever

-0.68

Daily

-0.66

ItemImage

-0.65

POSITIVE LOGITS

xff

1.24

xc

1.01

xe

1.00

xb

0.99

xa

0.96

xd

0.96

0.94

xes

0.82

0.80

uden

0.78

Activations Density 7.908%

detailed numerical data, including measurements, percentages, and specific values

No Comments

No Known Activations