INDEX

Explanations

proper nouns referring to specific individuals

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

EMS

-0.96

yrinth

-0.81

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.80

irth

-0.79

qua

-0.78

Interstitial

-0.76

 confir

-0.76

iership

-0.75

PLIED

-0.74

Constructed

-0.73

POSITIVE LOGITS

TOM

0.91

 named

0.86

 aliases

0.84

 Alvin

0.83

named

0.83

 surn

0.79

 Nemesis

0.79

ames

0.78

aniel

0.78

bard

0.77

Activations Density 5.713%

proper nouns referring to specific individuals

No Comments

No Known Activations