INDEX

Explanations

phrases related to organizations and their operations

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

ĪĴ

-1.20

¥µ

-1.17

EStream

-0.85

RTX

-0.77

thing

-0.77

 Unch

-0.77

gered

-0.76

journal

-0.75

¶æ

-0.75

 Columbia

-0.74

POSITIVE LOGITS

orporated

1.82

arcer

1.74

hester

1.61

orpor

1.51

idence

1.43

identally

1.40

orrect

1.38

redible

1.37

endiary

1.34

redibly

1.27

Activations Density 5.908%

phrases related to organizations and their operations

No Comments

No Known Activations