INDEX

Explanations

mentions of the term "Pen" at a high level of activation

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

 mono

-0.65

orically

-0.56

ãĤ·

-0.56

åį

-0.55

à¦

-0.55

ãĥŁ

-0.54

vag

-0.54

è¦ļéĨĴ

-0.54

ä½¿

-0.54

ÑĢ

-0.53

POSITIVE LOGITS

cil

1.32

alties

1.12

elope

1.09

itent

1.02

insula

0.98

nington

0.91

esville

0.86

ning

0.85

etr

0.82

issance

0.82

Activations Density 7.810%

mentions of the term "Pen" at a high level of activation

No Comments

No Known Activations