INDEX

Explanations

code snippets within JSON objects

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

osate

-0.64

rolet

-0.63

 Alger

-0.63

Faw

-0.61

anamo

-0.59

 Boko

-0.59

etheless

-0.58

 Nightmares

-0.56

 Azerbai

-0.56

 Franco

-0.56

POSITIVE LOGITS

catentry

0.92

Attributes

0.87

ItemImage

0.85

ItemThumbnailImage

0.81

title

0.73

sell

0.71

soType

0.70

price

0.70

isSpecialOrderable

0.68

quickShipAvailable

0.67

Activations Density 8.418%

code snippets within JSON objects

No Comments

No Known Activations