INDEX

Explanations

expressions of power ratings in watts

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

Quantities, often followed by units of measure

np_acts-logits-general · gemini-2.0-flash

units of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

TopLevel

-0.53

 bể

-0.53

acamata

-0.52

 كومونز

-0.51

τεύ

-0.50

cámara

-0.50

InstanceState

-0.50

cionales

-0.49

kyou

-0.49

 ProgressDialog

-0.48

POSITIVE LOGITS

mAh

0.65

rpm

0.64

rpm

0.62

mAh

0.61

RPM

0.56

 frigor

0.56

 kasarigan

0.54

mah

0.54

円

0.51

RPM

0.51

Activations Density 0.335%

expressions of power ratings in watts

Quantities, often followed by units of measure

units of measurement

No Comments

No Known Activations