INDEX

Explanations

prepositions indicating relationships or connections between concepts

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

prepositions followed by articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 informée

-0.57

 noqa

-0.42

AccessorTable

-0.41

ViewFeatures

-0.40

taxonomy

-0.40

AnimationsModule

-0.39

RefNanny

-0.39

 ""],

-0.39

 ?>">

-0.38

enumi

-0.38

POSITIVE LOGITS

InstrumentedTest

0.69

styleType

0.50

prepareStatement

0.49

Jeografia

0.49

EndGlobalSection

0.49

Personensuche

0.48

weightedMode

0.48

uxxxx

0.46

 GenerationType

0.46

цездатний

0.45

Activations Density 0.311%

prepositions indicating relationships or connections between concepts

prepositions followed by articles

No Comments

No Known Activations