INDEX

Explanations

elements of code or syntax used in programming documentation

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 HasFactory

-0.55

艋

-0.43

InputBorder

-0.43

TypedDataSet

-0.39

transpiration

-0.38

jewództ

-0.37

civi

-0.36

slam

-0.36

fromnode

-0.36

 ویکی

-0.35

POSITIVE LOGITS

KURZBESCHREIBUNG

0.47

hoeddwyd

0.47

">—

0.46

")));

0.46

craina

0.45

 мәкал

0.43

 مشين

0.43

 ModelExpression

0.43

__*/

0.42

</tfoot>

0.41

Activations Density 0.002%

elements of code or syntax used in programming documentation

No Comments

No Known Activations