INDEX

Explanations

terms related to measurements and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 lenker

-0.43

garbage

-0.42

sidemargin

-0.40

OGND

-0.39

 crumbs

-0.39

 Schemes

-0.39

ViewImports

-0.38

SCHEME

-0.37

breadcrumbs

-0.37

 actionPerformed

-0.36

POSITIVE LOGITS

 quantity

1.46

 Quantity

1.45

Quantity

1.44

Quanti

1.41

quantity

1.40

quanti

1.39

 Quanti

1.37

 quanti

1.34

 QUANT

1.26

 quantitative

1.25

Activations Density 0.105%

terms related to measurements and quantities

No Comments

No Known Activations