INDEX

Explanations

numerical expressions related to statistical results and models

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

Hyphens/dashes followed by a numeral

np_acts-logits-general · gemini-2.0-flash

statistical methods and citations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ⓧ

-0.68

таратура

-0.60

 nonUne

-0.58

 Signalez

-0.57

 poveznice

-0.56

 purpoſe

-0.56

MLLoader

-0.56

 nonatomic

-0.56

 HttpNotFound

-0.54

逅

-0.54

POSITIVE LOGITS

="">

0.61

 tartalomajánló

0.51

signable

0.51

BlockSize

0.49

inerja

0.48

 zusammenge

0.46

featureID

0.45

ynx

0.44

↘

0.44

 sprayed

0.44

Activations Density 0.093%

numerical expressions related to statistical results and models

Hyphens/dashes followed by a numeral

statistical methods and citations

No Comments

No Known Activations