INDEX

Explanations

terms related to role-playing games, specifically items and equipment such as scrolls, enchantments, armor, and weapons

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

aceous

-0.51

ername

-0.48

 bidder

-0.44

chens

-0.44

 filib

-0.44

ttle

-0.43

 interviewer

-0.42

phalt

-0.42

 camer

-0.42

orian

-0.41

POSITIVE LOGITS

 Revelation

0.53

 course

0.48

 Wisdom

0.47

 enchantment

0.47

 Minerva

0.47

 Promise

0.46

 Fate

0.46

rium

0.45

icial

0.44

 Regener

0.44

Activations Density 8.196%

terms related to role-playing games, specifically items and equipment such as scrolls, enchantments, armor, and weapons

No Comments

No Known Activations