INDEX

Explanations

References to political figures, parties, and nominations related to the Republican Party and the presidential election

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

krit

-1.08

pots

-0.95

trak

-0.95

adr

-0.93

kok

-0.92

ensitive

-0.92

dropping

-0.91

hooting

-0.91

chell

-0.91

abiding

-0.91

POSITIVE LOGITS

 Party

1.31

 nominee

1.17

 strongh

1.12

 presidential

1.12

 stronghold

1.10

 frontrunner

1.08

 hopeful

1.04

 primaries

1.01

 candidate

0.99

 candidates

0.98

Activations Density 8.273%

References to political figures, parties, and nominations related to the Republican Party and the presidential election

No Comments

No Known Activations