INDEX

Explanations

references to financial transactions and exchange rates

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

strap

-1.24

ulhu

-1.21

zzle

-1.16

gets

-1.13

jac

-1.12

stra

-1.12

isi

-1.12

à©

-1.04

igsaw

-1.03

ahon

-1.03

POSITIVE LOGITS

ably

1.39

prise

1.32

folios

1.23

places

1.22

tainment

1.18

 traded

1.16

able

1.16

prises

1.15

 exchange

1.12

ability

1.12

Activations Density 0.984%

references to financial transactions and exchange rates

No Comments

No Known Activations