INDEX

Explanations

terms related to measurements and assessments in scientific or clinical contexts

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

after capitalized words

np_acts-logits-general · gemini-2.0-flash

analysis, properties, configurations, receipt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

OGND

-0.82

 وتسجيلات

-0.74

 صوتيه

-0.68

 ویکی‌پدی

-0.62

 autorytatywna

-0.60

 Administrativna

-0.60

 يتيمه

-0.59

ConstraintMaker

-0.59

 Chwiliwch

-0.57

tagHelperRunner

-0.56

POSITIVE LOGITS

bootstrapcdn

0.35

intenant

0.34

 Púb

0.33

 Comun

0.33

skj

0.33

 Conſ

0.32

 Escolar

0.32

 Houſe

0.32

UnifiedTopology

0.31

stateProvider

0.31

Activations Density 0.533%

terms related to measurements and assessments in scientific or clinical contexts

after capitalized words

analysis, properties, configurations, receipt

No Comments

No Known Activations