INDEX

Explanations

structured data elements, primarily within XML or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RegressionTest

-0.59

oshima

-0.59

 '\\;'

-0.58

stylers

-0.54

ForValue

-0.53

الحياه

-0.52

Portale

-0.52

ANTLR

-0.50

ColumnHeaders

-0.50

mapreduce

-0.49

POSITIVE LOGITS

.*")]

0.69

endphp

0.60

 coussin

0.58

#+#

0.57

 élas

0.56

AxisAlignment

0.56

帖最后由

0.56

 समीक्षक

0.53

 صوتيه

0.53

enumi

0.53

Activations Density 0.867%

structured data elements, primarily within XML or programming contexts

No Comments

No Known Activations