INDEX

Explanations

proper nouns and names

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Literatuur

-0.47

 AssemblyCulture

-0.41

 craindre

-0.40

Fordítás

-0.40

 mijne

-0.40

})();

-0.38

 beroep

-0.38

yorlar

-0.37

 ویکی‌پدی

-0.36

 abstrato

-0.36

POSITIVE LOGITS

inex

0.55

nix

0.52

 Verm

0.48

 InputDecoration

0.46

 BufferedImage

0.46

ardes

0.45

Nix

0.45

 viewDidLoad

0.44

markets

0.44

hers

0.44

Activations Density 0.137%

proper nouns and names

No Comments

No Known Activations