INDEX

Explanations

sequences of numbers related to physical measurements or monetary values

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

odic

-0.72

alid

-0.72

alez

-0.69

unal

-0.64

arial

-0.64

essen

-0.61

icides

-0.60

kell

-0.60

alien

-0.59

airs

-0.59

POSITIVE LOGITS

MHz

0.82

MHz

0.72

mAh

0.68

NX

0.64

0.62

IU

0.62

 calories

0.61

 meters

0.60

xp

0.60

 Mile

0.60

Activations Density 10.019%

sequences of numbers related to physical measurements or monetary values

No Comments

No Known Activations