INDEX

Explanations

instances of the substring "qu" in various forms

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

Tokens starting with "Qu" followed by other letters

np_acts-logits-general · gemini-2.0-flash

words starting with Qu

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

 itſelf

-0.74

 GenerationType

-0.74

+:+

-0.72

verwijspagina

-0.71

لينكات

-0.68

出版年

-0.68

WebElementEntity

-0.66

 MessageBoxIcon

-0.64

 onOptions

-0.63

 Benedetto

-0.63

POSITIVE LOGITS

Qu

0.74

qu

0.73

Qu

0.62

QU

0.61

qu

0.53

copg

0.48

 quas

0.46

Extinguishing

0.45

reportWebVitals

0.44

QU

0.44

Activations Density 0.078%

instances of the substring "qu" in various forms

Tokens starting with "Qu" followed by other letters

words starting with Qu

No Comments

No Known Activations