INDEX

Explanations

phrases indicating associations or relationships between concepts

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

associated with

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

جغرافيا

-0.42

¡¡

-0.39

ChildScrollView

-0.38

SharedDtor

-0.36

converted

-0.35

 moglie

-0.34

십시오

-0.34

 kysy

-0.34

decide

-0.31

:✨

-0.31

POSITIVE LOGITS

 ASSOCIATED

0.66

 associated

0.65

 Associated

0.63

Associated

0.62

 ویکی‌پدی

0.60

associated

0.59

 asoci

0.55

 ассо

0.54

 associations

0.54

 association

0.54

Activations Density 0.056%

phrases indicating associations or relationships between concepts

associated with

No Comments

No Known Activations

phrases indicating associations or relationships between concepts

associated with

No Comments

No Known Activations