INDEX

Explanations

references to different types of areas or spaces

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

area nearest, area of

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

HomeAsUpEnabled

-0.38

ąb

-0.37

 kidna

-0.35

sendKeys

-0.35

 mision

-0.35

 remplacement

-0.33

spy

-0.32

 Investigaciones

-0.32

 erros

-0.31

 spion

-0.31

POSITIVE LOGITS

area

0.76

 betweenstory

0.75

 area

0.75

 Areas

0.72

Area

0.72

 Area

0.71

areas

0.71

Bereich

0.70

GraphicsUnit

0.66

 AREA

0.65

Activations Density 0.020%

references to different types of areas or spaces

area nearest, area of

No Comments

No Known Activations