INDEX

Explanations

references to testing or quality assurance processes

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

testing and tested

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 disambiguazione

-0.56

 esternos

-0.55

 tartalomajánló

-0.54

expandindo

-0.52

ParallelGroup

-0.52

 transférez

-0.51

 ostavi

-0.51

 المعيارى

-0.50

 виправивши

-0.50

 kaarangay

-0.50

POSITIVE LOGITS

 testing

0.45

 pruebas

0.45

 Tested

0.43

Tested

0.43

 Testing

0.42

Testing

0.41

 tested

0.40

 TESTING

0.38

测试

0.38

tested

0.38

Activations Density 0.014%

references to testing or quality assurance processes

testing and tested

No Comments

No Known Activations