INDEX

Explanations

structured data or code snippets related to databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Rptr

-0.50

 BoxFit

-0.48

usda

-0.45

BindingResult

-0.44

sourceType

-0.43

 poti

-0.43

ModelAdmin

-0.43

<sub>

-0.42

 espe

-0.41

</thead>

-0.40

POSITIVE LOGITS

Personendaten

1.03

 للاسماء

0.97

richTextPanel

0.90

Билгалдахарш

0.89

 kaarangay

0.82

SourceChecksum

0.80

Spoljašnje

0.80

Autoritní

0.78

__':

0.76

SerializedSize

0.75

Activations Density 0.161%

structured data or code snippets related to databases

No Comments

No Known Activations