INDEX

Explanations

programming terms and structures related to data management and manipulation

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

Code that adds items to lists

np_acts-logits-general · gemini-2.0-flash

adding or pushing to lists

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

存于互联网档案馆

-0.63

 ͡°)

-0.62

Diwedd

-0.61

RenderAtEndOf

-0.60

 Chwiliwch

-0.59

)](

-0.58

 initComponents

-0.58

}])

-0.58

 Sélectionnez

-0.57

GEBURTSDATUM

-0.57

POSITIVE LOGITS

 addObject

0.67

の中では

0.66

 بيها

0.66

の中で

0.62

 containing

0.61

 contains

0.59

webElementGuid

0.59

contains

0.59

BeginContext

0.58

 single

0.56

Activations Density 0.131%

programming terms and structures related to data management and manipulation

Code that adds items to lists

adding or pushing to lists

No Comments

No Known Activations