INDEX

Explanations

references to games and gaming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

middels

-0.89

 CreateTagHelper

-0.86

ostante

-0.86

weile

-0.86

kepada

-0.83

forChild

-0.82

 CrossRef

-0.79

hauled

-0.79

SBATCH

-0.78

%;">

-0.78

POSITIVE LOGITS

 games

1.67

 game

1.45

 Game

1.42

games

1.40

 Games

1.39

game

1.32

 GAME

1.26

Game

1.24

Games

1.22

GAME

1.20

Activations Density 0.040%

references to games and gaming

No Comments

No Known Activations