INDEX

Explanations

references to "giant" or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 pylint

-0.39

endregion

-0.38

MigrationBuilder

-0.36

archiviato

-0.34

 ReactDOM

-0.34

zzleHttp

-0.34

TagHelpers

-0.33

ResumeLayout

-0.33

 infected

-0.33

xsl

-0.32

POSITIVE LOGITS

Specialist

0.93

 specialist

0.91

specialist

0.89

 Specialist

0.88

Communities

0.86

 Communities

0.83

communities

0.79

 communities

0.78

 Analyst

0.70

 communautés

0.67

Activations Density 0.083%

references to "giant" or related concepts

No Comments

No Known Activations