INDEX

Explanations

references to specific technical terms or acronyms, such as 'MB' or 'GP', that are commonly used in a technical or specialized context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

coni

-0.83

zona

-0.75

apons

-0.73

ãĥīãĥ©ãĤ´ãĥ³

-0.69

ources

-0.67

Interstitial

-0.67

aways

-0.66

ãĥ³ãĤ¸

-0.66

Ò

-0.63

xit

-0.62

POSITIVE LOGITS

iotic

1.04

uild

1.01

edded

1.00

ilib

0.97

iosis

0.94

iotics

0.92

odies

0.90

olicy

0.89

illion

0.86

arrass

0.82

Activations Density 5.324%

references to specific technical terms or acronyms, such as 'MB' or 'GP', that are commonly used in a technical or specialized context

No Comments

No Known Activations