INDEX

Explanations

scientific terms and their specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

раздо

-0.41

 Kelas

-0.39

 corpi

-0.38

цездатний

-0.38

 bibliographies

-0.37

 dolci

-0.37

__*/

-0.35

 trời

-0.34

Спасылкі

-0.33

zionalità

-0.33

POSITIVE LOGITS

makeConstraints

0.54

Hentet

0.49

RectangleBorder

0.48

دانشنامهٔ

0.48

UrlResolution

0.47

ScopeManager

0.45

StoryboardSegue

0.45

openhague

0.45

StackNavigator

0.44

 AttributeSet

0.44

Activations Density 1.462%

scientific terms and their specific contexts

No Comments

No Known Activations