INDEX

Explanations

technical terminology and measurements related to particle physics experiments

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

"at," "in," "of," after certain words

np_acts-logits-general · gemini-2.0-flash

LEP, at, number

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.76

AlterField

-0.73

<?

-0.66

 arşivlendi

-0.63

 ferons

-0.62

 AssemblyCulture

-0.61

########.

-0.61

ConstraintMaker

-0.61

+#+

-0.60

VersionUID

-0.59

POSITIVE LOGITS

 gluon

0.50

 hard

0.49

tonsoft

0.48

pow

0.48

jets

0.47

يمه

0.45

 yağ

0.45

pow

0.45

 scot

0.44

 harde

0.44

Activations Density 0.534%

technical terminology and measurements related to particle physics experiments

"at," "in," "of," after certain words

LEP, at, number

No Comments

No Known Activations