INDEX

Explanations

information related to costs and expenses

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

AppData

-0.63

witch

-0.61

soType

-0.59

ittees

-0.59

ulla

-0.58

gdala

-0.58

orative

-0.58

Ü

-0.57

phasis

-0.57

amber

-0.56

POSITIVE LOGITS

 incurred

0.72

 upkeep

0.70

 goods

0.68

 incarcer

0.65

 maintaining

0.64

 acquiring

0.62

 transportation

0.61

 incarceration

0.60

 extortion

0.60

 manpower

0.59

Activations Density 12.094%

information related to costs and expenses

No Comments

No Known Activations