INDEX

Explanations

references to mathematical properties related to sets and functions, specifically those that are non-empty, non-zero, or involving specific algebraic conditions

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

"Non-zero" or "non empty" conditions

np_acts-logits-general · gemini-2.0-flash

non-zero or non-empty values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 simplest

-0.36

asiest

-0.35

ardan

-0.34

 Grünen

-0.34

êtement

-0.33

(()

-0.32

Tại

-0.32

àm

-0.31

onerror

-0.31

</h6>

-0.31

POSITIVE LOGITS

isNotEmpty

0.75

 nonzero

0.69

 nontrivial

0.66

NotNil

0.66

NotNull

0.66

NotEmpty

0.66

IsNotEmpty

0.64

Diweddarwch

0.62

isNotBlank

0.61

notNull

0.59

Activations Density 0.761%

references to mathematical properties related to sets and functions, specifically those that are non-empty, non-zero, or involving specific algebraic conditions

"Non-zero" or "non empty" conditions

non-zero or non-empty values

No Comments

No Known Activations