INDEX

Explanations

different elements of a technical document related to programming languages and user guides

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

ONSORED

-0.81

KEN

-0.70

agle

-0.69

ishment

-0.68

ÃŃs

-0.68

aste

-0.66

ãĤ´

-0.65

edia

-0.64

agen

-0.64

west

-0.63

POSITIVE LOGITS

 assorted

0.89

markets

0.80

 wallets

0.80

 warranties

0.78

 personalities

0.78

 histories

0.77

 portfolios

0.74

etc

0.73

 swaps

0.71

 cabinets

0.71

Activations Density 15.710%

different elements of a technical document related to programming languages and user guides

No Comments

No Known Activations