INDEX

Explanations

instances where the word "alone" is used to indicate being by oneself or without others

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

 decay

-0.52

 Skydragon

-0.50

wed

-0.49

imal

-0.49

 GENERAL

-0.47

mit

-0.46

roxy

-0.46

mun

-0.45

inders

-0.45

 Junk

-0.45

POSITIVE LOGITS

 culp

0.55

ativity

0.55

 skeptics

0.52

 accus

0.51

ingen

0.48

asio

0.48

otti

0.48

ta

0.47

gebra

0.47

 exoner

0.46

Activations Density 10.291%

instances where the word "alone" is used to indicate being by oneself or without others

No Comments

No Known Activations