INDEX

Explanations

references to images and their usefulness

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

after specific punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

mathematical formulas and numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

MLLoader

-0.48

 surla

-0.47

XmlAccessorType

-0.45

 الحره

-0.37

Ehrungen

-0.37

ellido

-0.36

 isNameExpr

-0.36

Bibliograf

-0.35

zug

-0.35

 آموزشی

-0.34

POSITIVE LOGITS

tagHelperRunner

0.46

 inilah

0.43

 Wikiseite

0.43

 nahilalakip

0.42

Kjelder

0.42

StructEnd

0.41

 Wirkung

0.41

sidemargin

0.41

ffilm

0.40

imageshack

0.40

Activations Density 0.246%

references to images and their usefulness

after specific punctuation or symbols

mathematical formulas and numbers

No Comments

No Known Activations