INDEX

Explanations

summaries and classifications of demographic, biological, or physical properties in research data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__*/

-0.96

 Audiodateien

-0.95

 estekak

-0.78

endphp

-0.77

 дописавши

-0.74

تقاوى

-0.72

ArrowToggle

-0.72

دانشنامهٔ

-0.72

ItemBackground

-0.72

 mergeFrom

-0.70

POSITIVE LOGITS

IVEREF

0.50

vin

0.49

Jäh

0.45

 induced

0.45

</h2>

0.41

 evoked

0.41

tuvo

0.41

 imputed

0.40

たびに

0.40

 principali

0.39

Activations Density 0.840%

summaries and classifications of demographic, biological, or physical properties in research data

No Comments

No Known Activations