INDEX

Explanations

elements related to structured data or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Rüyada

-0.58

 Vogt

-0.52

tille

-0.51

roa

-0.49

 Mendoza

-0.49

 Rosenthal

-0.48

ced

-0.48

basePath

-0.47

ruta

-0.47

 trail

-0.46

POSITIVE LOGITS

 الحره

0.91

Wasn

0.73

InstanceState

0.72

__":

0.72

ViewImports

0.71

RetentionPolicy

0.71

 Roskov

0.68

AlterField

0.68

0.66

 Wouldn

0.64

Activations Density 2.559%

elements related to structured data or code

No Comments

No Known Activations