INDEX

Explanations

references to notable publications or organizations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.87

 transfieras

-0.66

\{\\

-0.63

IUrlHelper

-0.60

الإنجليزية

-0.56

onViewCreated

-0.54

basicConfig

-0.54

bindingNavigator

-0.53

 newBuilder

-0.51

waitKey

-0.50

POSITIVE LOGITS

Morfo

0.62

Palmar

0.56

 Baillargeon

0.53

*@

0.51

 lenker

0.51

 ovvero

0.51

atorium

0.51

")(

0.50

 TextAppearance

0.50

netbeans

0.50

Activations Density 0.280%

references to notable publications or organizations

No Comments

No Known Activations