INDEX

Explanations

the word "Gen" or variations of it

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

cffffcc

-1.03

Hour

-0.95

TPPStreamerBot

-0.94

vati

-0.92

eneg

-0.91

letal

-0.88

deen

-0.88

 Princ

-0.87

 Hour

-0.87

©¶æ

-0.85

POSITIVE LOGITS

uine

1.99

ocide

1.86

iuses

1.61

esis

1.52

omics

1.51

etically

1.47

uin

1.41

omic

1.32

etics

1.29

oses

1.28

Activations Density 1.042%

the word "Gen" or variations of it

No Comments

No Known Activations