INDEX

Explanations

mathematical notations and symbols related to measure theory and functional analysis

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

mathematical notation $L^2$

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

 initComponents

-0.62



-0.55

AlterField

-0.53

 estekak

-0.52

 <<<<<<<<<<<<<<

-0.52

ंदीखरीदारी

-0.51

expandindo

-0.51

PerformLayout

-0.50



-0.50

請繼續往下閱讀

-0.50

POSITIVE LOGITS

 norme

0.42

 szary

0.41

 pungkas

0.40

 waard

0.39

 blijven

0.38

tissu

0.38

 препратки

0.37

 bezit

0.36

 variétés

0.35

 trouw

0.35

Activations Density 0.208%

mathematical notations and symbols related to measure theory and functional analysis

mathematical notation $L^2$

No Comments

No Known Activations