INDEX

Explanations

historical information and significant events

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

vg

-0.69

igger

-0.57

riz

-0.56

ander

-0.56

ventures

-0.54

and

-0.53

giene

-0.52

lot

-0.52

elo

-0.52

ger

-0.50

POSITIVE LOGITS

 Known

0.65

 Published

0.57

Available

0.55

 Available

0.55

 intimidated

0.54

 Speaking

0.53

 Asked

0.51

 Called

0.51

 Serving

0.50

 Released

0.49

Activations Density 7.590%

historical information and significant events

No Comments

No Known Activations