INDEX

Explanations

instances of the word "pun" and related expressions, indicating a focus on humor or wordplay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

########.

-0.72

ⓧ

-0.60

Obrázky

-0.58

uurs

-0.55

IsPostBack

-0.53

gameserver

-0.51

ьаж

-0.50

Initializable

-0.50

 InputDecoration

-0.50

laye

-0.49

POSITIVE LOGITS

Personensuche

0.94

pun

0.59

farande

0.59

 sufficient

0.58

ما

0.56

Specialty

0.55

YLON

0.54

 specialty

0.54

 speciality

0.53

Espèce

0.52

Activations Density 2.592%

instances of the word "pun" and related expressions, indicating a focus on humor or wordplay

No Comments

No Known Activations