INDEX

Explanations

keywords related to computer programming or technical documentation

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

rosso

-0.79

 Ging

-0.78

 pockets

-0.76

 snowball

-0.72

 eleph

-0.68

 Gorge

-0.68

 elig

-0.67

 plateau

-0.66

Hut

-0.66

 crossover

-0.65

POSITIVE LOGITS

 ILCS

0.82

ÙĲ

0.80

Ùİ

0.79

0.77

eah

0.77

dfx

0.77

\/

0.76

ESE

0.75

Īè

0.75

0.74

Activations Density 6.981%

keywords related to computer programming or technical documentation

No Comments

No Known Activations