INDEX

Explanations

characteristics or patterns involving negative and positive values or indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Eleventh

-0.67

ValueStyle

-0.66

 eleventh

-0.66

 twelfth

-0.62

 leprosy

-0.50

 navideña

-0.50

IconModule

-0.49

 Sanger

-0.49

 navideño

-0.49

isseau

-0.49

POSITIVE LOGITS

 PropTypes

0.62

queryInterface

0.58

LogFactory

0.53

stateProvider

0.52

 intptr

0.49

 Wiktionnaire

0.49

 Exactos

0.48

AccessorTable

0.47

keyColumn

0.47

rrggbb

0.47

Activations Density 0.461%

characteristics or patterns involving negative and positive values or indicators

No Comments

No Known Activations