INDEX

Explanations

technical terms and keywords related to software licenses and documentation

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

software headers and licensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

дента

-0.50

Jeografia

-0.49

 препратки

-0.47

itinéraire

-0.47

webElementXpaths

-0.44

 Paglinawan

-0.39

 مرئيه

-0.36

 webdriver

-0.36

 rowspan

-0.36

 engineering

-0.34

POSITIVE LOGITS

tagHelperRunner

0.67

 AssemblyTitle

0.61

/*++

0.54



0.53

ASF

0.53

EFIAPI

0.52

AndroidJUnit

0.49

enderror

0.49

featureID

0.46

ьаж

0.46

Activations Density 0.019%

technical terms and keywords related to software licenses and documentation

software headers and licensing

No Comments

No Known Activations