INDEX

Explanations

keywords related to locks and security measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issance

-0.94

LV

-0.88

PsyNetMessage

-0.80

OTAL

-0.80

anse

-0.77

acio

-0.76

opausal

-0.74

oun

-0.73

abama

-0.73

resso

-0.73

POSITIVE LOGITS

picking

1.57

heed

1.45

pick

1.27

creen

1.26

lear

1.19

hart

1.16

downs

1.14

down

1.10

yer

1.08

hold

1.06

Activations Density 7.005%

keywords related to locks and security measures

No Comments

No Known Activations