INDEX

Explanations

names of public figures or entities

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

ffen

-0.66

trak

-0.65

Kap

-0.65

vana

-0.61

 Caval

-0.61

Lap

-0.60

Lag

-0.59

manship

-0.58

 Kamp

-0.58

 Pastebin

-0.57

POSITIVE LOGITS

cious

0.96

ãĤ¼ãĤ¦ãĤ¹

0.89

utical

0.82

ioxide

0.79

etary

0.78

rencies

0.77

ervative

0.74

ervatives

0.74

ountain

0.73

İ

0.73

Activations Density 8.954%

names of public figures or entities

No Comments

No Known Activations