INDEX

Explanations

phrases related to the value or importance of concepts or ideas

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

dayName

-0.69

 istg

-0.60

herer

-0.59

swick

-0.59

arta

-0.58

dit

-0.58

Ã¦

-0.56

hew

-0.56

cohol

-0.56

ague

-0.55

POSITIVE LOGITS

 teamwork

0.67

 preserving

0.66

 these

0.64

 unborn

0.56

 Nanto

0.55

 mankind

0.55

 investing

0.55

inese

0.54

 incumb

0.54

 balancing

0.54

Activations Density 13.345%

phrases related to the value or importance of concepts or ideas

No Comments

No Known Activations