INDEX

Explanations

references to social media and promotional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

OGND

-0.84

ScopeManager

-0.81

parsedMessage

-0.80

PMailer

-0.65

 betweenstory

-0.64

AccessorTable

-0.63

ftagPool

-0.63

elemField

-0.55

webElementXpaths

-0.54

exitRule

-0.54

POSITIVE LOGITS

 intptr

0.35

ConverterFactory

0.35

 existentes

0.35

 pię

0.33

 brand

0.33

 väh

0.32

 vuotta

0.32

पया

0.32

eseorang

0.31

 userData

0.31

Activations Density 0.208%

references to social media and promotional content

No Comments

No Known Activations