INDEX

Explanations

categories and entities related to media and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

Similar

-0.42

〒

-0.39

whether

-0.38

 Analog

-0.37

same

-0.37

Same

-0.36

Either

-0.35

other

-0.35

syntax

-0.34

 hoga

-0.34

POSITIVE LOGITS

 like

0.87

 likes

0.73

อย่าง

0.60

NameInMap

0.59

 Мексичка

0.59

 tartalomajánló

0.58

GEBURTSDATUM

0.56

parsedMessage

0.55

 liking

0.55

تقاوى

0.55

Activations Density 0.245%

categories and entities related to media and technology

No Comments

No Known Activations