INDEX

Explanations

references to health impacts and emotional factors in various contexts

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

preceding "as" or related to physicality

np_acts-logits-general · gemini-2.0-flash

physical health and states

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

 onPostExecute

-0.57

مراجع

-0.55

AndroidJUnit

-0.54

NOPQRST

-0.49

GOTREF

-0.49

classnames

-0.49

madu

-0.45

NgModule

-0.45

Batis

-0.44

到处

-0.43

POSITIVE LOGITS

 physical

1.29

 technical

1.08

physical

1.07

 Physical

1.07

 PHYSICAL

1.05

Physical

1.05

PHYSICAL

1.03

 physically

1.03

物理

0.97

 technological

0.92

Activations Density 0.453%

references to health impacts and emotional factors in various contexts

preceding "as" or related to physicality

physical health and states

No Comments

No Known Activations