INDEX

Explanations

mentions of governmental and legal entities and their activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ingen

-0.41

uckland

-0.40

selection

-0.39

uku

-0.39

antry

-0.39

hole

-0.38

gow

-0.38

ibaba

-0.38

ukemia

-0.38

hov

-0.38

POSITIVE LOGITS

 Commission

0.49

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.46

 Fighters

0.41

 Disorder

0.40

 Branch

0.39

 Coliseum

0.39

 Zone

0.39

 Standards

0.39

 Railroad

0.39

 License

0.39

Activations Density 6.895%

mentions of governmental and legal entities and their activities

No Comments

No Known Activations