INDEX

Explanations

references to varying degrees of quality or standards in products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

+#+#

-0.56

 læng

-0.55

#+#

-0.50

 echi

-0.48

Japon

-0.47

 vandens

-0.45

GN

-0.45

maxlen

-0.45

клопе

-0.44

 scheda

-0.44

POSITIVE LOGITS

 betweenstory

0.81

ViewImports

0.80

 насељу

0.79

oa̍t

0.76

 lenker

0.72

 cherchés

0.71

`;

0.70

StructEnd

0.70

Демографія

0.69

Datuak

0.67

Activations Density 0.192%

references to varying degrees of quality or standards in products or experiences

No Comments

No Known Activations