INDEX

Explanations

there are no significant activation patterns, indicating it does not have a specific target or focus within the document

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

Code, statistics, or measurements with a name and value

np_acts-logits-general · gemini-2.0-flash

stat name and value attributes

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

 المعيارى

-0.73

exitRule

-0.69

 незавершена

-0.62

webElementXpaths

-0.59

 BorderSide

-0.59

WithIOException

-0.59

 AllMovie

-0.57

 expédi

-0.54

DispatchToProps

-0.54

 diversité

-0.54

POSITIVE LOGITS

 calculation

0.90

 calculations

0.84

Calculation

0.84

 calculated

0.84

 calculate

0.83

 Calculated

0.83

 estimations

0.82

 Calculation

0.82

 measurement

0.81

 measured

0.80

Activations Density 0.311%

there are no significant activation patterns, indicating it does not have a specific target or focus within the document

Code, statistics, or measurements with a name and value

stat name and value attributes

No Comments

No Known Activations