INDEX

Explanations

instances of mathematical notation or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 kaarangay

-0.85

oa̍t

-0.67

󠁴

-0.66

Personendaten

-0.65

 initComponents

-0.65

 мәкал

-0.61

﹧

-0.61

kloped

-0.60

 Okada

-0.59

IndentedString

-0.59

POSITIVE LOGITS

</tbody>

0.83

IMPORTED

0.54

the

0.48

end

0.45

<thead>

0.45

LikeLiked

0.44

</tr>

0.42

<table>

0.42

 kind

0.41

PREFERRED

0.41

Activations Density 0.037%

instances of mathematical notation or expressions

No Comments

No Known Activations