INDEX

Explanations

technology-related terms and specifics related to development frameworks like Angular, Docker, and Google Analytics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rontal

-0.92

 rays

-0.90

 symbolism

-0.89

 caut

-0.87

 largeDownload

-0.86

aft

-0.85

lax

-0.85

cffffcc

-0.85

ãĥĸ

-0.83

 bribes

-0.82

POSITIVE LOGITS

builder

0.98

Pub

0.95

wright

0.91

 mates

0.87

Linux

0.87

iverse

0.86

neys

0.85

Â¶

0.85

owner

0.84

else

0.83

Activations Density 2.483%

technology-related terms and specifics related to development frameworks like Angular, Docker, and Google Analytics

No Comments

No Known Activations