INDEX

Explanations

elements related to humor and irony in storytelling

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Features by Cosine Similarity

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Plots

Explanation

Show Test Field

Default Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 '\\;'

-0.72

liosis

-0.68

SuppressMessage

-0.60

uxxxx

-0.59

ännande

-0.57

Obrázky

-0.56

 snippetHide

-0.56

 résistant

-0.56

 utford

-0.56

Personensuche

-0.55

POSITIVE LOGITS

 contrived

0.99

 unnecessarily

0.98

 cringe

0.98

 overly

0.97

 needlessly

0.93

 unnecessary

0.92

 tacky

0.89

🤮

0.89

 awkwardly

0.87

 pointless

0.87

Activations Density 0.317%

elements related to humor and irony in storytelling

No Activations Uploaded