INDEX

Explanations

references to statistics or measurements related to performance

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

reflect time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

səhifə

-0.60

 IFTT

-0.55

 Photocase

-0.53

 JpaRepository

-0.52

GEBURTSDATUM

-0.52

المكان

-0.52

bindingNavigator

-0.51

userdetails

-0.51



-0.51

 Taktlose

-0.50

POSITIVE LOGITS

+#+

0.68

########.

0.57

))))))))

0.37

 <<<<<<<<<<<<<<

0.36

}}}}

0.36

↵↵

0.34

GeoNames

0.33

GOTREF

0.33

 Yesterday

0.32

])))

0.32

Activations Density 0.000%

references to statistics or measurements related to performance

reflect time

No Comments

No Known Activations