INDEX

Explanations

various types of comments and documentation formatting in code

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

Code comments or header-like content

np_acts-logits-general · gemini-2.0-flash

code comments and syntax

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

 كومونز

-0.72

دانشنامهٔ

-0.70

клопе

-0.69

 ModelExpression

-0.68

Aiheesta

-0.66

InjectAttribute

-0.64

($__

-0.64

تقاوى

-0.63

jsxFileName

-0.62

 незавершена

-0.62

POSITIVE LOGITS

↵

0.59

0.51

 AssemblyCompany

0.50

"]:

0.49

 useContext

0.49

__).

0.47

↵↵

0.47

0.46

}`}>

0.45

yntaxException

0.45

Activations Density 0.283%

various types of comments and documentation formatting in code

Code comments or header-like content

code comments and syntax

No Comments

No Known Activations