INDEX

Explanations

articles and demonstratives in text

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

"The" preceding nouns

np_acts-logits-general · gemini-2.0-flash

the following of "The"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

<eos>

-1.08

)))));

-0.57

 RIPRODUZIONE

-0.56

__);

-0.54

))));

-0.52

 ?...

-0.48

>>;

-0.48

ertia

-0.47

 medesimo

-0.45

!...

-0.44

POSITIVE LOGITS

 film

0.80

 album

0.73

 المعيارى

0.70

 city

0.70

 book

0.70

 Senate

0.68

 United

0.67

 government

0.67

 programme

0.67

 song

0.67

Activations Density 1.234%

articles and demonstratives in text

"The" preceding nouns

the following of "The"

No Comments

No Known Activations

articles and demonstratives in text

"The" preceding nouns

the following of "The"

No Comments

No Known Activations