INDEX

Explanations

mathematical terms and symbols related to statistical modeling and estimation

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

mathematical probability and estimation

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

存于互联网档案馆

-0.52

 autorytatywna

-0.50

tagHelperRunner

-0.49

OGND

-0.46

]<<"

-0.45

 للاسماء

-0.42

MLLoader

-0.40

IContainer

-0.40

epam

-0.39

writeFieldEnd

-0.38

POSITIVE LOGITS

setdefault

0.43

SOUNDBITE

0.38

tionalität

0.38

 Tempat

0.37

Toponymie

0.36

execSQL

0.36

 casada

0.36

 Taktlose

0.35

 hjemmes

0.35

 Auflösung

0.35

Activations Density 0.132%

mathematical terms and symbols related to statistical modeling and estimation

mathematical probability and estimation

No Comments

No Known Activations