INDEX

Explanations

punctuation marks and their associated formatting

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

Follows "Q:" or "#" in text

np_acts-logits-general · gemini-2.0-flash

Observatory 1998 than

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 الرياضيه

-0.65

:✨

-0.60

Brainz

-0.60

 lenker

-0.58

IBinder

-0.55

__*/

-0.55

choon

-0.55

Rujuakan

-0.53

/*---

-0.51

DebuggerNonUser

-0.51

POSITIVE LOGITS

askets

0.59

ernalia

0.58

 contextLoads

0.56

ientôt

0.56

}}/>

0.53

rentices

0.53

/><

0.53

jahtera

0.51

 disambiguazione

0.51

האם

0.51

Activations Density 0.037%

punctuation marks and their associated formatting

Follows "Q:" or "#" in text

Observatory 1998 than

No Comments

No Known Activations