INDEX

Explanations

interrogative phrases and questions

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

"Are" followed by a pronoun

np_acts-logits-general · gemini-2.0-flash

are you questions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.65

 Jefus

-0.63

 itſelf

-0.57

CodedInputStream

-0.56

 AppComponent

-0.54

 Chrift

-0.53

 Himself

-0.52

 Anybody

-0.52

 Réponses

-0.52

 himſelf

-0.51

POSITIVE LOGITS

we

1.09

you

0.94

 they

0.84

 AssemblyCulture

0.75

wir

0.67

 мы

0.62

wij

0.61

you

0.60

']],

0.60

 فريبيس

0.59

Activations Density 0.100%

interrogative phrases and questions

"Are" followed by a pronoun

are you questions

No Comments

No Known Activations