INDEX

Explanations

references to placing or handling items, particularly in the context of food or personal objects

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

Prepositions followed by possessive pronouns

np_acts-logits-general · gemini-2.0-flash

preposition followed by possessive or article

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

queryInterface

-0.52

 estimés

-0.51

 Jambi

-0.50

γραφία

-0.49

ServiceModel

-0.49

FXML

-0.49

RefNanny

-0.49

AccessorTable

-0.49

vertis

-0.49

 XNUMX

-0.49

POSITIVE LOGITS

awtextra

0.76

DrawerToggle

0.65

 ivelany

0.61

OrNil

0.58

uxxxx

0.55

شهاد

0.54

abestanden

0.53

<?

0.51

Shallow

0.51

 erwähnt

0.48

Activations Density 0.230%

references to placing or handling items, particularly in the context of food or personal objects

Prepositions followed by possessive pronouns

preposition followed by possessive or article

No Comments

No Known Activations