INDEX

Explanations

statistical patterns and measurements related to biological studies

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

Numbers or symbols followed by "is", "were," or "means"

np_acts-logits-general · gemini-2.0-flash

numbers two means deletion or amplification

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HasForeignKey

-0.60

nologies

-0.57

cademia

-0.51

 StatelessWidget

-0.51

PERATURE

-0.49

olic

-0.48

Did

-0.47

 whiteColor

-0.46

WithFormat

-0.46

 förm

-0.46

POSITIVE LOGITS

 esetén

0.64

 kaarangay

0.63

 automatically

0.61

ConstraintMaker

0.60

HomeAsUpEnabled

0.57

 automáticamente

0.57

 Orrell

0.56

Дереккөздер

0.55

 apapun

0.54

 Réponses

0.54

Activations Density 0.557%

statistical patterns and measurements related to biological studies

Numbers or symbols followed by "is", "were," or "means"

numbers two means deletion or amplification

No Comments

No Known Activations