INDEX

Explanations

language related to return policies and customer service interactions

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

Following "for," "agreement," or numeric tokens

np_acts-logits-general · gemini-2.0-flash

agreement three

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

 justement

-0.45

Apparently

-0.42

ItemBackground

-0.41

supposed

-0.40

providedIn

-0.40

Legături

-0.40

 vrais

-0.40

Кстати

-0.39

setVerticalGroup

-0.38

 beetje

-0.38

POSITIVE LOGITS

 please

0.79

 Please

0.67

Please

0.65

please

0.62

 requested

0.57

 PLEASE

0.57

 requests

0.56

 Италијани

0.55

 olacaktır

0.55

PLEASE

0.54

Activations Density 0.626%

language related to return policies and customer service interactions

Following "for," "agreement," or numeric tokens

agreement three

No Comments

No Known Activations