INDEX

Explanations

personal names and entities with acronyms or initials

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦ļéĨĴ

-0.74

ihu

-0.72

odore

-0.72

ourning

-0.68

 unloaded

-0.63

icz

-0.62

LOS

-0.61

upt

-0.60

osate

-0.59

 mourning

-0.58

POSITIVE LOGITS

iors

0.71

cess

0.71

export

0.68

aneous

0.68

media

0.67

ities

0.67

enced

0.66

ibly

0.65

ibles

0.65

Ger

0.64

Activations Density 0.929%

personal names and entities with acronyms or initials

No Comments

No Known Activations