INDEX

Explanations

mathematical notations and symbols

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

s-large or s-small

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

 ProtoMessage

-0.49

webElementXpaths

-0.47

VYMaps

-0.42

#+#

-0.40

 sederhana

-0.36

 vicenda

-0.36

 geblieben

-0.36

 GreatSchools

-0.35

 gioco

-0.34

 zabaw

-0.34

POSITIVE LOGITS

 تانيه

0.65

RTEE

0.62

AddTagHelper

0.57

 defaultstate

0.54

 ujednoznacz

0.54

IVEREF

0.53

'{@

0.52

endphp

0.52

Erreferentziak

0.51

 للمعارف

0.50

Activations Density 0.202%

mathematical notations and symbols

s-large or s-small

No Comments

No Known Activations