INDEX

Explanations

instances of humor and laughter

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ecore

-0.62

anoke

-0.59

коменду

-0.58

Bes

-0.58

znik

-0.57

 Hain

-0.57

Bronnen

-0.56

 Kane

-0.55

 hvilken

-0.54

RegistryLite

-0.51

POSITIVE LOGITS

 Laughter

1.48

 laughter

1.31

 Laugh

1.27

 Laughing

1.21

 laugh

1.21

 laughs

1.18

 laughing

1.16

 laughed

1.14

Laughter

1.09

 lachen

1.07

Activations Density 0.092%

instances of humor and laughter

No Comments

No Known Activations