INDEX

Explanations

elements related to numerical data and statistical representation

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

litter-mate control hearts

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

Спољашње

-0.51

 disponibilités

-0.50

 itinéraires

-0.49

extAlignment

-0.49

 ModelExpression

-0.47

Cyl

-0.47

脚注の使い方

-0.47

 propOrder

-0.46

arker

-0.45

 defaultstate

-0.45

POSITIVE LOGITS

Personendaten

0.35

 Administrativna

0.35

évaluateur

0.35

 متعلقه

0.33

 useAppContext

0.30

zeiti

0.30

rsiniz

0.29

MeasureSpec

0.29

 rojas

0.29

mbggenerated

0.28

Activations Density 0.011%

elements related to numerical data and statistical representation

litter-mate control hearts

No Comments

No Known Activations

elements related to numerical data and statistical representation

litter-mate control hearts

No Comments

No Known Activations