INDEX

Explanations

mathematical symbols and notation commonly used in formal proofs and definitions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adaptiveStyles

-0.81

 ExecuteAsync

-0.64

PreferredItem

-0.62

setObjectName

-0.61

ItemBackground

-0.60

$_['

-0.59

 contextLoads

-0.59

 אז

-0.58

ลอง

-0.58

=$("#

-0.57

POSITIVE LOGITS

PMailer

0.63

ukkig

0.60

Luckily

0.56

 Luckily

0.56

Fortunately

0.55

幸好

0.54

 Fortunately

0.52

receta

0.52

compared

0.52

 personne

0.51

Activations Density 0.180%

mathematical symbols and notation commonly used in formal proofs and definitions

No Comments

No Known Activations