INDEX

Explanations

references to structured data or categories related to software and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 linkovi

-0.38

 either

-0.36

 ivelany

-0.36

 usually

-0.35

either

-0.35

lo

-0.34

hos

-0.34

 preceding

-0.33

ppl

-0.33

POSITIVE LOGITS

:✨

1.61

Portail

0.63

قایناق‌لار

0.60

 للاسماء

0.60

 Verſ

0.56

erintah

0.54

 AttributeSet

0.54

AsUp

0.51

rbrakk

0.50

Datuak

0.49

Activations Density 0.013%

references to structured data or categories related to software and systems

No Comments

No Known Activations