INDEX

Explanations

scientific terms and processes related to experiments and measurements

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

 arşivlendi

-0.54

 utafitiHapana

-0.53

EndProject

-0.50

SharedDtor

-0.47

хьтан

-0.46

脚注の使い方

-0.45

IsContent

-0.44

ciatore

-0.42

IZABETH

-0.42

 BytesLike

-0.41

POSITIVE LOGITS

 preparation

0.45

preparation

0.43

 prepara

0.41

 preparatory

0.40

parsedMessage

0.40

prep

0.39

 prépar

0.39

 stabilization

0.39

Prepar

0.39

 Preparation

0.39

Activations Density 0.176%

scientific terms and processes related to experiments and measurements

No Comments

No Known Activations