INDEX

Explanations

parentheses and their contents

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

Parenthetical phrases

np_acts-logits-general · gemini-2.0-flash

birth and death dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 تضيفلها

-0.60

None

-0.50

 Either

-0.49

NamedQueries

-0.47

 None

-0.46

numberOfLines

-0.43

.-

-0.43

AntiForgeryToken

-0.43

sety

-0.43

ificazione

-0.43

POSITIVE LOGITS

also

1.19

pictured

1.18

now

1.10

formerly

1.07

originally

1.07

previously

1.04

aka

1.00

hence

0.97

pronounced

0.97

above

0.96

Activations Density 0.297%

parentheses and their contents

Parenthetical phrases

birth and death dates

No Comments

No Known Activations