INDEX

Explanations

conclusions and summaries in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 resourceCulture

-0.86

 فريبيس

-0.83

adaptiveStyles

-0.82

KommentareTeilen

-0.77

</tfoot>

-0.75

 متعلقه

-0.74

EndContext

-0.74

Gambas

-0.73

 ErrIntOverflow

-0.73

+:+

-0.73

POSITIVE LOGITS

Conclusion

0.81

\/

0.67

/**

0.65

 Honda

0.61

 substance

0.60

 émotion

0.59

Honda

0.56

 Conclusion

0.54

Promise

0.54

 Foster

0.54

Activations Density 0.147%

conclusions and summaries in text

No Comments

No Known Activations