INDEX

Explanations

mentions of specific roles and responsibilities within a company or organization

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

nered

-0.28

scape

-0.26

pan

-0.26

sov

-0.24

rated

-0.24

church

-0.24

fell

-0.23

uro

-0.23

shaw

-0.23

spons

-0.22

POSITIVE LOGITS

 checkout

0.29

 Sloan

0.26

 Marie

0.26

 clerk

0.25

 Elaine

0.25

 maid

0.25

 clerks

0.24

 Anne

0.23

BIL

0.23

halla

0.23

Activations Density 8.053%

mentions of specific roles and responsibilities within a company or organization

No Comments

No Known Activations