INDEX

Explanations

information or mentions related to confidentiality, anonymity, or speaking off the record

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

ney

-0.58

charg

-0.57

tons

-0.52

abase

-0.52

cer

-0.49

nant

-0.49

nard

-0.46

RAM

-0.44

 cider

-0.44

ONS

-0.44

POSITIVE LOGITS

 anonymity

0.85

ously

0.67

 anonym

0.65

 pseudonym

0.57

 anonymously

0.55

ãĥĩ

0.55

 Flavoring

0.55

 afforded

0.54

 shrouded

0.52

Downloadha

0.51

Activations Density 10.444%

information or mentions related to confidentiality, anonymity, or speaking off the record

No Comments

No Known Activations