INDEX

Explanations

references to judges or judging in the context of talent shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ujednoznacz

-0.90

Diweddarwch

-0.70

tagHelperRunner

-0.68

rungsseite

-0.67

 Waray

-0.66

ChildScrollView

-0.63

 ſehr

-0.63



-0.61

<unused28>

-0.60

<unused16>

-0.60

POSITIVE LOGITS

 judge

0.34

 ausz

0.26

파

0.25

 tweeted

0.25

getColumnIndex

0.24

 defaultstate

0.24

 judges

0.24

TResult

0.24

 juiz

0.24

 فت

0.24

Activations Density 0.009%

references to judges or judging in the context of talent shows

No Comments

No Known Activations