INDEX

Explanations

mentions of taxpayer money and expenses

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

appa

-0.85

 Marble

-0.84

lime

-0.83

 Bour

-0.83

azes

-0.83

 Jacket

-0.82

 Thing

-0.81

iu

-0.80

 Finder

-0.80

 Glob

-0.80

POSITIVE LOGITS

payers

1.30

 taxpayers

1.22

 subsid

1.18

ridor

1.14

payer

1.13

 dollars

1.07

 bailed

1.07

berus

1.05

 taxpayer

1.04

 subsidized

1.00

Activations Density 1.016%

mentions of taxpayer money and expenses

No Comments

No Known Activations