INDEX

Explanations

references to models and their specifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 polega

-0.42

 şeyler

-0.41

zędu

-0.39

mités

-0.39

 Wohnung

-0.37

 robić

-0.36

 państw

-0.36

 moeder

-0.35

 wynika

-0.35

 Begründung

-0.35

POSITIVE LOGITS

 Series

0.69

 series

0.68

 SERIES

0.67

 models

0.64

 سری

0.60

Series

0.60

SERIES

0.59

 serie

0.55

series

0.55

シリーズ

0.53

Activations Density 0.233%

references to models and their specifications

No Comments

No Known Activations