INDEX

Explanations

numerical data representing statistical results and their variations

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

numbers with ±

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

LookAnd

-0.61

 Wikiseite

-0.60

yarnpkg

-0.60

 wikipagina

-0.60

 Мексичка

-0.57

 Offisielt

-0.55

 BoxDecoration

-0.51

richTextPanel

-0.50

 صوتيه

-0.49

protetor

-0.48

POSITIVE LOGITS

 wireType

0.55

ScopeManager

0.37

bate

0.34

 seta

0.32

 changes

0.31

AccessException

0.30

ramanian

0.30

 stderr

0.30

BeforeClass

0.29

 twists

0.29

Activations Density 0.145%

numerical data representing statistical results and their variations

numbers with ±

No Comments

No Known Activations