INDEX

Explanations

code or markup syntax elements

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

math notation with mu

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 للاسماء

-0.80

 AssemblyCulture

-0.79

 незавершена

-0.76

цездатний

-0.75

oa̍t

-0.74

 Италијани

-0.74

 المعيارى

-0.72

afficheront

-0.70

 OFDb

-0.70

 resourceCulture

-0.69

POSITIVE LOGITS

endphp

0.47

[]:

0.31

Fast

0.30

Gold

0.30

PreExecute

0.29

 кот

0.28

jande

0.28

 Gold

0.28

jon

0.27

BB

0.27

Activations Density 0.001%

code or markup syntax elements

math notation with mu

No Comments

No Known Activations