INDEX

Explanations

instances of the word "woke" followed by a numerical value

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

inates

-0.71

orously

-0.70

 Britann

-0.69

regate

-0.69

inate

-0.68

ietal

-0.67

esan

-0.66

berman

-0.65

lette

-0.64

coni

-0.63

POSITIVE LOGITS

mares

1.17

wake

0.92

 refreshed

0.86

 awake

0.86

 awoke

0.85

 awaken

0.84

 woke

0.77

mare

0.76

 Nightmares

0.72

akens

0.71

Activations Density 8.548%

instances of the word "woke" followed by a numerical value

No Comments

No Known Activations