INDEX

Explanations

punctuation marks, specifically periods

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

`.` or `<start_of_turn>` followed by specific words

np_acts-logits-general · gemini-2.0-flash

java.util classes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 disambiguazione

-0.67

ViewInit

-0.66

Šaltiniai

-0.66

MigrationBuilder

-0.62

abstractmethod

-0.57

blurRadius

-0.56

CloseOperation

-0.56

 MainAxisSize

-0.55

Sklici

-0.55

 الرياضيه

-0.55

POSITIVE LOGITS

 list

0.55

ArrayList

0.43

List

0.42

 varias

0.41

gathering

0.41

 List

0.41

 gathering

0.39

list

0.39

bag

0.39

 random

0.38

Activations Density 0.018%

punctuation marks, specifically periods

`.` or `<start_of_turn>` followed by specific words

java.util classes

No Comments

No Known Activations