INDEX

Explanations

parentheses and associated numeric values in medical or technical contexts

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

Text within parentheses

np_acts-logits-general · gemini-2.0-flash

acronyms followed by descriptive terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyProduct

-0.63

市镇

-0.62

 الرياضيه

-0.59

 chì

-0.55

tahui

-0.51

Бахар

-0.50

AndEndTag

-0.48

外部リンク

-0.47

verifyException

-0.47

 Juga

-0.47

POSITIVE LOGITS

UIControlState

0.68

 كومونز

0.62

̓

0.61

yntaxException

0.58

bonucleic

0.57

__':

0.56

 AssemblyTitle

0.56

">//

0.52

HostException

0.52

LEncoder

0.52

Activations Density 0.209%

parentheses and associated numeric values in medical or technical contexts

Text within parentheses

acronyms followed by descriptive terms

No Comments

No Known Activations