INDEX

Explanations

content that reveals insincerity or sarcasm in communication

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

DoubleQuotes

-0.49

 Wikipédia

-0.49

 саны

-0.47

wikidata

-0.47

 docente

-0.44

Peu

-0.43

Память

-0.43

DataAnnotations

-0.43

킴

-0.42

ベージュ

-0.42

POSITIVE LOGITS

 initComponents

0.77

 fancy

0.74

 fanfare

0.69

########.

0.68

ioutil

0.67

 blah

0.66

شهاد

0.64

huh

0.62

 hyped

0.60

 ErrIntOverflow

0.59

Activations Density 0.374%

content that reveals insincerity or sarcasm in communication

No Comments

No Known Activations