INDEX

Explanations

terms denoting the significance or necessity of concepts and practices in various contexts

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

essential for success or function

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.67

 Вікіпе

-0.60

OGND

-0.54

windowFixed

-0.54

المكان

-0.54

msgSender

-0.53

tanleria

-0.52

揄

-0.49

<tfoot>

-0.49

Чыгана

-0.48

POSITIVE LOGITS

 aspect

0.88

 aspects

0.77

 part

0.75

 importance

0.70

aspect

0.67

 aspectos

0.62

 element

0.61

 aspek

0.60

 onderdeel

0.59

 important

0.59

Activations Density 0.038%

terms denoting the significance or necessity of concepts and practices in various contexts

essential for success or function

No Comments

No Known Activations