INDEX

Explanations

mathematical expressions and notations indicating relationships between variables in a theoretical context

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

adaptiveStyles

-0.65

RectangleBorder

-0.60

 recevrez

-0.60

ValueStyle

-0.59

IActionResult

-0.58

setObjectName

-0.56

 متعلقه

-0.55

 remercier

-0.54

IBOutlet

-0.53

udadera

-0.53

POSITIVE LOGITS

webElement

0.63

енча

0.59

WebElementEntity

0.59

AndEndTag

0.55

 civilisation

0.53

sizeCache

0.49

 ReactDOM

0.49

WireFormat

0.48

 vPvB

0.47

 postIndex

0.47

Activations Density 0.630%

mathematical expressions and notations indicating relationships between variables in a theoretical context

No Comments

No Known Activations