INDEX

Explanations

expressions and references to humor, laughter, and related emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.63

ecore

-0.58

IsContent

-0.51

skaya

-0.48

神宮

-0.47

лючение

-0.47

 onPostExecute

-0.47

prefixer

-0.47

GMENT

-0.47

Overnight

-0.47

POSITIVE LOGITS

 laugh

1.50

 laughing

1.44

 laughter

1.44

 Laughter

1.43

 comedy

1.41

 laughs

1.36

 laughed

1.34

 jokes

1.31

 humour

1.26

 joke

1.26

Activations Density 0.172%

expressions and references to humor, laughter, and related emotions

No Comments

No Known Activations