INDEX

Explanations

interactive elements and queries in a dialogue scenario

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

Code-related words and symbols

np_acts-logits-general · gemini-2.0-flash

quotation marks and punctuation

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

]!='

-0.70

 beginnetje

-0.64

 hObject

-0.63

RTEE

-0.57

GEBURTSDATUM

-0.54

WithIdentifier

-0.52

\#:

-0.52

sī

-0.52

Portail

-0.51

rungsseite

-0.51

POSITIVE LOGITS

 GenerationType

0.56

 ویکی‌آمباردا

0.51

 EconPapers

0.50

hagy

0.50

pédie

0.50

POV

0.48

acán

0.47

DrawerToggle

0.46

ặt

0.46

asuring

0.46

Activations Density 0.105%

interactive elements and queries in a dialogue scenario

Code-related words and symbols

quotation marks and punctuation

No Comments

No Known Activations