INDEX

Explanations

words associated with real estate

oai_token-act-pair · gemini-2.0-flash

I am sorry, I cannot provide a clear explanation. The activations are fragmented and do not clearly relate to the top positive logits

np_token-act-pair-logits · gemini-2.0-flash

Properties and accommodations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.68

LayoutStyle

-0.65

 humaines

-0.54

 bordada

-0.54

 Himo

-0.54

copus

-0.54

migrationBuilder

-0.53

nameof

-0.52

 bordados

-0.50

esgue

-0.50

POSITIVE LOGITS

invokeLater

0.58

autoreleasepool

0.52

 HttpNotFound

0.52

Obrázky

0.52

ngilizce

0.52

 surla

0.50

RegressionTest

0.48

 StringField

0.46

([]

0.45

 Seeder

0.45

Activations Density 1.005%

words associated with real estate

I am sorry, I cannot provide a clear explanation. The activations are fragmented and do not clearly relate to the top positive logits

Properties and accommodations

No Comments

No Known Activations