INDEX

Explanations

mathematical symbols and expressions, particularly related to equations and referencing within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Discography

-0.70

 GRAN

-0.63

 jSON

-0.63

Sü

-0.60

Ró

-0.60

 Hidup

-0.60

 Stef

-0.59

Zey

-0.59

Edg

-0.58

Recur

-0.56

POSITIVE LOGITS

1.67

&=&

1.25

</th>

1.22

)&

1.15

>&

1.14

">&

1.10

:&

1.10

%&

1.09

}&

1.09

*&

1.08

Activations Density 0.093%

mathematical symbols and expressions, particularly related to equations and referencing within documents

No Comments

No Known Activations