INDEX

Explanations

mathematical expressions or formulas being defined or represented

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

 Administrativna

-0.77

Portail

-0.73

OGND

-0.68

ंदीखरीदारी

-0.67

 يتيمه

-0.65



-0.64

WaitGroup

-0.64

 سكانية

-0.63

parsedMessage

-0.63

Rüyada

-0.63

POSITIVE LOGITS

 lautet

0.46

 следу

0.44

 following

0.41

0.39

 suivante

0.39

 shown

0.37

 entry

0.37

 follows

0.36

如下

0.36

following

0.36

Activations Density 1.194%

mathematical expressions or formulas being defined or represented

No Comments

No Known Activations