INDEX

Explanations

references to specific samples and patient data in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

onio

-0.41

physical

-0.40

 Dossier

-0.40

 GRAM

-0.38

publication

-0.38

 calcium

-0.38

 verm

-0.38

 Durga

-0.37

vibr

-0.36

 validation

-0.36

POSITIVE LOGITS

CloseOperation

0.62

ⓧ

0.62

 AttributeSet

0.56

principalTable

0.49

 Verhältnisse

0.49

 Geſch

0.49

 désert

0.48

 "]";

0.48

ніципалі

0.48

LookAnd

0.47

Activations Density 1.436%

references to specific samples and patient data in a research context

No Comments

No Known Activations