INDEX

Explanations

occurrences of asterisks or similar characters

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

Asterisks surrounded by numbers

np_acts-logits-general · gemini-2.0-flash

legal citation numbers

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

hasMoreElements

-0.63

ioutil

-0.56

==",

-0.54

zval

-0.53

zeera

-0.52

herjee

-0.51

cor

-0.50

OrUpdate

-0.50

zeitig

-0.50

-0.49

POSITIVE LOGITS

********

1.28

*********

1.26

**********

1.22

************

1.20

****************

1.20

*************

1.17

***********

1.16

***************

1.15

 okuyayım

1.12

?*

1.11

Activations Density 0.859%

occurrences of asterisks or similar characters

Asterisks surrounded by numbers

legal citation numbers

No Comments

No Known Activations