INDEX

Explanations

phrases that indicate causation or reasoning

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

createStatement

-0.48

readFileSync

-0.43

 insuffisamment

-0.42

 Suivez

-0.42

prepareStatement

-0.41

fromJson

-0.40

لاعب

-0.40

 tijden

-0.40

 algoritmo

-0.40

اقرأ

-0.39

POSITIVE LOGITS

Vidite

0.62

why

0.59

 kaarangay

0.57

 مشين

0.54

 ویکی‌پدی

0.54

сюда

0.49

 PeEnEo

0.48

why

0.48

 Administrativna

0.47

hence

0.47

Activations Density 0.011%

phrases that indicate causation or reasoning

No Comments

No Known Activations