INDEX

Explanations

phrases that express agreement or affirmation

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

"And" followed by discourse markers

np_acts-logits-general · gemini-2.0-flash

And followed by connector words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</caption>

-0.71

ikyuu

-0.70

eseorang

-0.59

 obstante

-0.56

UrlResolution

-0.55

])/

-0.55

etcode

-0.53

""".

-0.52

}}">

-0.51

()]

-0.51

POSITIVE LOGITS

TintMode

0.73

And

0.72

yes

0.70

 виправивши

0.70

WebVitals

0.69

 مشين

0.68

 NSCoder

0.66

 cannibal

0.65

AccessorTable

0.65

رشف

0.63

Activations Density 0.156%

phrases that express agreement or affirmation

"And" followed by discourse markers

And followed by connector words

No Comments

No Known Activations