INDEX

Explanations

words related to law enforcement and police leadership

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

ted

-0.48

ngth

-0.46

ajor

-0.46

mented

-0.46

ROR

-0.42

pmwiki

-0.42

ubuntu

-0.42

pez

-0.41

nel

-0.40

PsyNetMessage

-0.40

POSITIVE LOGITS

 Petty

0.48

 Chief

0.44

doms

0.43

Chief

0.43

 Chiefs

0.39

Jay

0.39

Boh

0.37

 Fritz

0.36

 Levels

0.36

 Council

0.35

Activations Density 9.749%

words related to law enforcement and police leadership

No Comments

No Known Activations