INDEX

Explanations

phrases indicating changes, increases, or comparisons in data or conditions

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

increase and growth

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

__':

-0.47

zzino

-0.45

hfill

-0.44

 فريبيس

-0.44

__':

-0.44

 intptr

-0.44

iwa

-0.44

__":

-0.43

ロウィン

-0.43

 Sulf

-0.42

POSITIVE LOGITS

 increase

0.68

increase

0.57

Increase

0.54

 Wachstum

0.54

 aumento

0.54

inSlope

0.52

 crecimiento

0.50

 Bioaccumulative

0.50

 increases

0.50

 Erhöhung

0.49

Activations Density 0.173%

phrases indicating changes, increases, or comparisons in data or conditions

increase and growth

No Comments

No Known Activations