INDEX

Explanations

structured data formats, particularly JSON-like syntax with objects and arrays

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

########.

-0.82

دانشنامهٔ

-0.82

 surla

-0.77

adaptiveStyles

-0.77

expandindo

-0.75

 للاسماء

-0.75

 وتسجيلات

-0.71

migrationBuilder

-0.71

KURZBESCHREIBUNG

-0.69

ValueStyle

-0.68

POSITIVE LOGITS

 ordf

0.55

 religieuses

0.55

 territoriale

0.53

})*/

0.52

 scolaires

0.52

 sanitarias

0.51

 potest

0.49

 beroep

0.47

})()

0.47

 orale

0.47

Activations Density 0.185%

structured data formats, particularly JSON-like syntax with objects and arrays

No Comments

No Known Activations