INDEX

Explanations

markers indicating the beginning of a new section or distinct segments in a document

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

Code, identifiers, or math symbols

np_acts-logits-general · gemini-2.0-flash

sequence of non-negative numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WebVitals

-0.65

 policiers

-0.59

 disambiguazione

-0.56

runApp

-0.55

pulumi

-0.51

InSection

-0.51

 CharSequence

-0.50

ytä

-0.50

 Englishmen

-0.49

GOTREF

-0.49

POSITIVE LOGITS

nesc

0.88

tinyos

0.79

دانشنامهٔ

0.67

 purs

0.64

 pellic

0.62

Atm

0.55

 Californie

0.53

例文帳に追加

0.53

tagHelperRunner

0.52

Lor

0.51

Activations Density 0.070%

markers indicating the beginning of a new section or distinct segments in a document

Code, identifiers, or math symbols

sequence of non-negative numbers

No Comments

No Known Activations