INDEX

Explanations

code comments and documentation markers in programming

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

Code-related symbols and comments

np_acts-logits-general · gemini-2.0-flash

code comments and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

webElementXpaths

-0.76

NameInMap

-0.72

 دیکھیے

-0.69

 protoimpl

-0.67

 كومونز

-0.66

ValueStyle

-0.65

Abitanti

-0.64

 Савезне

-0.64

ActionCreators

-0.60

 препратки

-0.59

POSITIVE LOGITS

/**

0.59

}}}

0.58

ⓧ

0.56

middag

0.55

/**

0.54

'},

0.54

Gets

0.53

')));

0.52

"),

0.49

/**

0.49

Activations Density 0.073%

code comments and documentation markers in programming

Code-related symbols and comments

code comments and programming constructs

No Comments

No Known Activations