INDEX

Explanations

words within comparative contexts ("lower cost", "reducing the footprint", "simplifies, improves", etc.) or words denoting the act of reduction itself

oai_token-act-pair · gemini-2.0-flash

cost reduction/efficiency

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Савезне

-0.87

SupportActionBar

-0.81

ChildScrollView

-0.79

PreExecute

-0.78

Personendaten

-0.77

yntaxException

-0.76

MemoryWarning

-0.75

Tikang

-0.75

HideFlags

-0.75

LookAnd

-0.74

POSITIVE LOGITS

Boy

0.38

ون

0.34

 over

0.33

sp

0.32

boy

0.32

बाह

0.31

 comunicarse

0.31

주

0.31

bo

0.31

ling

0.30

Activations Density 1.403%

words within comparative contexts ("lower cost", "reducing the footprint", "simplifies, improves", etc.) or words denoting the act of reduction itself

cost reduction/efficiency

No Comments

No Known Activations