INDEX

Explanations

political and legislative terms and discussions

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

ngth

-0.86

href

-0.71

ĸļ

-0.68

catentry

-0.67

²¾

-0.66

ãĤ¼ãĤ¦ãĤ¹

-0.65

OIL

-0.65

ulnerability

-0.63

¿½

-0.63

ForgeModLoader

-0.62

POSITIVE LOGITS

 votes

1.03

 unanimously

1.01

 ballot

0.98

 vote

0.95

 referendum

0.94

 ballots

0.92

votes

0.90

 Votes

0.90

 refere

0.89

 elections

0.85

Activations Density 24.001%

political and legislative terms and discussions

No Comments

No Known Activations