INDEX

Explanations

proper nouns, specifically names

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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.91

wings

-0.68

 Cerberus

-0.65

ãĤ¤ãĥĪ

-0.64

è¦ļéĨĴ

-0.63

WIND

-0.62

 Weinstein

-0.62

GROUND

-0.62

Ultra

-0.61

enance

-0.61

POSITIVE LOGITS

eties

1.26

uity

1.08

olas

1.04

otine

1.04

otin

0.99

opher

0.98

ety

0.95

kel

0.95

oshenko

0.94

asio

0.94

Activations Density 5.977%

proper nouns, specifically names

No Comments

No Known Activations