INDEX

Explanations

specific visual elements or labels in graphical representations or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

titleMargin

-0.68

pagestyle

-0.63

riwal

-0.62

AsUp

-0.58

 resourceCulture

-0.57

hæng

-0.57

 Italijanski

-0.56

AnchorStyles

-0.55

knecht

-0.53

nościo

-0.53

POSITIVE LOGITS

while

0.55

 mentre

0.54

 للاسماء

0.52

 <<<<<<<<<<<<<<

0.52

whereas

0.49

 while

0.49

 terwijl

0.48

 Sedangkan

0.47

 tandis

0.47

 ενώ

0.46

Activations Density 0.795%

specific visual elements or labels in graphical representations or figures

No Comments

No Known Activations