INDEX

Explanations

references to "grand" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

PreferredItem

-0.50

SourceChecksum

-0.50

ViewImports

-0.49

parsedMessage

-0.47

Pum

-0.47

 sanitarias

-0.45

istoitu

-0.44

windigkeit

-0.41

 Associated

-0.41

cury

-0.40

POSITIVE LOGITS

Rap

0.81

rap

0.76

Rap

0.71

RAP

0.69

RAP

0.69

 grand

0.67

rap

0.66

Rab

0.65

grand

0.63

Grand

0.62

Activations Density 0.391%

references to "grand" in various contexts

No Comments

No Known Activations