INDEX

Explanations

references to various software technologies and tools, such as event-driven frameworks, database systems, message libraries, and networking engines

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

verted

-0.93

ivity

-0.81

ential

-0.80

away

-0.75

encia

-0.73

ional

-0.70

=-=-=-=-=-=-=-=-

-0.68

ifts

-0.68

================================================================

-0.67

ibly

-0.67

POSITIVE LOGITS

iami

0.90

uppet

0.90

emonic

0.90

useum

0.90

ONEY

0.89

unicip

0.86

afia

0.86

insk

0.84

hattan

0.84

 Mayhem

0.83

Activations Density 5.038%

references to various software technologies and tools, such as event-driven frameworks, database systems, message libraries, and networking engines

No Comments

No Known Activations