INDEX

Explanations

references to documents and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GEBURTSDATUM

-0.54

Personensuche

-0.47

 onStart

-0.40

 BorderSide

-0.38

 enfans

-0.38

FilterChain

-0.38

 creș

-0.36

ăsp

-0.36

ută

-0.35

AnimationsModule

-0.34

POSITIVE LOGITS

 documents

3.06

documents

2.61

 Documents

2.59

Documents

2.45

 DOCUMENTS

2.22

 documentos

2.00

 Dokumente

1.78

 документы

1.63

 documenti

1.53

Documentos

1.42

Activations Density 0.144%

references to documents and documentation

No Comments

No Known Activations