INDEX

Explanations

relationships and comparisons between different concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

XmlAccessType

-0.43

Tembelea

-0.42

Tikang

-0.39

WaitGroup

-0.39

 NUKAT

-0.38

 خارجية

-0.37

 NgModule

-0.37

Personendaten

-0.36

出版年

-0.36

rodalom

-0.34

POSITIVE LOGITS

 beat

1.98

 beats

1.88

 surpass

1.80

 surpasses

1.79

 surpassed

1.79

 beating

1.70

 surpassing

1.67

 beaten

1.51

 Beat

1.48

beat

1.47

Activations Density 0.951%

relationships and comparisons between different concepts or entities

No Comments

No Known Activations