INDEX

Explanations

specific patterns related to electrical engineering, probably focusing on transistor properties and measurements

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

DragonMagazine

-1.41

pmwiki

-1.32

Reviewer

-1.24

Downloadha

-1.16

sbm

-1.14

Reloaded

-1.11

maxwell

-1.08

omething

-1.08

ische

-1.03

HCR

-1.02

POSITIVE LOGITS

 Trainer

0.79

Luo

0.75

Qi

0.75

Wu

0.74

paw

0.74

Roe

0.72

 Cruz

0.71

Yue

0.71

 Kingston

0.70

 Yoshi

0.70

Activations Density 6.938%

specific patterns related to electrical engineering, probably focusing on transistor properties and measurements

No Comments

No Known Activations