INDEX

Explanations

numerical values related to data or statistical measures in a document

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

The number 3

np_acts-logits-general · gemini-2.0-flash

the number 3

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

stination

-0.77

avelength

-0.70

tellations

-0.66

VIAF

-0.65

reditation

-0.65

atisfaction

-0.64

ArgumentParser

-0.63

 getLocation

-0.63

 DataLoader

-0.62

 Lawton

-0.62

POSITIVE LOGITS

1.48

３

0.73

 trente

0.71

0.67

۳

0.65

0.64

0.63

 treinta

0.59

rd

0.57

 Third

0.57

Activations Density 1.272%

numerical values related to data or statistical measures in a document

The number 3

the number 3

No Comments

No Known Activations