INDEX

Explanations

expressions and mentions of opinions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 бла

-0.78

■■

-0.70

delaire

-0.68

ьаж

-0.67

/***/

-0.63

Pvt

-0.63

endish

-0.63

برز

-0.63

 Byzantium

-0.61

lojik

-0.61

POSITIVE LOGITS

 Opinion

1.47

 opinion

1.46

 opinions

1.41

 Opinions

1.35

opinion

1.32

 Opin

1.30

Opinion

1.19

Opinions

1.16

opinions

1.16

 OPINION

1.15

Activations Density 0.091%

expressions and mentions of opinions

No Comments

No Known Activations