INDEX

Explanations

names and abbreviations related to various geographic locations and organizations

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

 IMAGES

-0.94

 schedules

-0.80

DragonMagazine

-0.80

iard

-0.79

 McCartney

-0.79

wagen

-0.78

headed

-0.78

 Iranians

-0.77

 Koreans

-0.77

 Kasich

-0.75

POSITIVE LOGITS

oteric

1.44

quire

1.42

earchers

1.37

sequ

1.20

pected

1.15

ury

1.14

ensible

1.14

ync

1.12

urance

1.11

ylum

1.10

Activations Density 1.049%

names and abbreviations related to various geographic locations and organizations

No Comments

No Known Activations

names and abbreviations related to various geographic locations and organizations

No Comments

No Known Activations