INDEX

Explanations

phrases related to emotional expressions and opinions

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

"of" followed by "the" or a possessive

np_acts-logits-general · gemini-2.0-flash

some of the

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

two

-0.67

 zweier

-0.57

 zwei

-0.56

 dwóch

-0.56

 deux

-0.55

two

-0.55

 three

-0.54

TWO

-0.51

 drei

-0.51

兩個

-0.49

POSITIVE LOGITS

 المعيارى

0.56

 Wiktionnaire

0.49

 younger

0.48

 finest

0.47

 nicest

0.47

 hardest

0.44

 newer

0.44

abstractmethod

0.44

ValueGenerated

0.44

Younger

0.42

Activations Density 0.110%

phrases related to emotional expressions and opinions

"of" followed by "the" or a possessive

some of the

No Comments

No Known Activations