INDEX

Explanations

technical terms and parameters associated with data files and object attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

最快更新

-0.63

MLLoader

-0.61

."</

-0.58

__*/

-0.56

 continúas

-0.55

KELEY

-0.54

,:);

-0.53

Rptr

-0.53

</tfoot>

-0.53

 {}));

-0.52

POSITIVE LOGITS

+#+#

0.84

0.83

↑

0.63

IUrlHelper

0.62

 uninsured

0.61

__':

0.61

Kjelder

0.60

 metav

0.60

 שוליים

0.58

__":

0.57

Activations Density 2.477%

technical terms and parameters associated with data files and object attributes

No Comments

No Known Activations