INDEX

Explanations

descriptions related to logistics, planning, and specific details within a complex setting

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

 Prior

-0.71

 Spani

-0.66

 Brune

-0.65

 precinct

-0.64

 Britons

-0.63

 Moff

-0.63

 Murd

-0.62

Prior

-0.59

 Duchess

-0.58

 Rothschild

-0.58

POSITIVE LOGITS

ELF

0.85

 gonna

0.79

pecially

0.78

selves

0.78

ustainable

0.76

 impossible

0.74

orno

0.74

self

0.74

uddenly

0.73

lightly

0.73

Activations Density 6.519%

descriptions related to logistics, planning, and specific details within a complex setting

No Comments

No Known Activations