INDEX

Explanations

references related to surveillance, government actions, and controversial incidents

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

Pwr

-0.43

 Archdemon

-0.36

ments

-0.34

 Worlds

-0.34

 Twenty

-0.33

ctica

-0.32

 Breaker

-0.31

heid

-0.31

 Archangel

-0.30

 Grid

-0.30

POSITIVE LOGITS

SEE

0.47

cheon

0.44

undai

0.42

iple

0.41

hips

0.40

pless

0.40

ating

0.39

KING

0.39

chery

0.39

ums

0.38

Activations Density 6.805%

references related to surveillance, government actions, and controversial incidents

No Comments

No Known Activations