INDEX

Explanations

terms related to online casino games and gambling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

rungsseite

-0.48

EndProject

-0.47

 Keats

-0.46

pture

-0.45

StoreMessageInfo

-0.45

icitis

-0.45

falgar

-0.45

EndGlobal

-0.43

kkende

-0.43

 arşivlendi

-0.42

POSITIVE LOGITS

 casino

1.06

 gambling

1.03

 casinos

1.02

 Gambling

0.92

 Casino

0.90

 gamblers

0.88

Casino

0.87

 Casinos

0.85

Gambling

0.85

casino

0.84

Activations Density 0.118%

terms related to online casino games and gambling

No Comments

No Known Activations