INDEX

Explanations

specific pricing and cost details associated with products or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.66

}")]

-0.63

cipar

-0.63

ArgsConstructor

-0.63

mallow

-0.61

expandindo

-0.60

])))

-0.60

 AssemblyTitle

-0.59

']?>

-0.59

antd

-0.58

POSITIVE LOGITS

per

0.84

per

0.65

 apiece

0.62

Per

0.61

lüğ

0.58

 yearly

0.57

Per

0.54

 שוליים

0.52

 price

0.52

 WebDriverWait

0.51

Activations Density 0.105%

specific pricing and cost details associated with products or events

No Comments

No Known Activations