INDEX

Explanations

structural elements indicative of document formatting

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

windowFixed

-0.76

 Matti

-0.72

 McCle

-0.69

 BoxFit

-0.68

 dand

-0.67

 Cuth

-0.66

ragment

-0.65

 Bewußt

-0.64

 KeyCode

-0.63

ofold

-0.63

POSITIVE LOGITS

hline

3.26

hdashline

1.26

cline

1.16

<tr>

1.14

</tr>

0.76

</tbody>

0.73

</table>

0.72

<tbody>

0.72

″]

0.72

</h5>

0.70

Activations Density 0.011%

structural elements indicative of document formatting

No Comments

No Known Activations