INDEX

Explanations

technical terms related to machine learning and medical information

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

Ħ¢

-1.08

©¶æ¥µ

-1.04

-+-+

-0.98

ĸļ

-0.96

ĪĴ

-0.94

reme

-0.92

ĵĺ

-0.91

olicy

-0.86

ĳå£«

-0.86

 Debor

-0.86

POSITIVE LOGITS

ted

1.33

uvian

1.27

uminati

1.23

 Nadu

1.21

aments

1.21

ibr

1.21

ocated

1.18

ibrary

1.17

ution

1.12

ogical

1.12

Activations Density 5.823%

technical terms related to machine learning and medical information

No Comments

No Known Activations