INDEX

Explanations

sentences and statements that convey information, particularly those that indicate a strong assertion or conclusion

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

Text within quotation marks

np_acts-logits-general · gemini-2.0-flash

direct quotes and attribution

np_acts-logits-general · gemini-2.5-flash-lite

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

verwijspagina

-0.66

 виправивши

-0.58

 tartalomajánló

-0.56

 beginnetje

-0.55

IntoConstraints

-0.51

 mại

-0.50

 pinulongan

-0.49

 onAnimation

-0.49

 naik

-0.49

تقاوى

-0.48

POSITIVE LOGITS

})()

0.64

“

0.63

})();

0.62

IsContent

0.61

 “.

0.58

})();

0.57

“.

0.57

 “...

0.56

Added

0.56

”.

0.55

Activations Density 0.035%

sentences and statements that convey information, particularly those that indicate a strong assertion or conclusion

Text within quotation marks

direct quotes and attribution

No Comments

No Known Activations