INDEX

Explanations

keywords and headings related to acknowledgments or notices in structured documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 consultato

-0.76

Portail

-0.72

expandindo

-0.66

 تضيفلها

-0.63

abestanden

-0.62

NUMX

-0.61

SPATH

-0.60

tagHelperRunner

-0.59

windowFixed

-0.59

ebenarnya

-0.59

POSITIVE LOGITS

***

0.49

uğ

0.49

----------------

0.49

 ihtiyac

0.48

**

0.47

 waard

0.47

</h3>

0.45

cama

0.45

!!!

0.45

 Augusta

0.45

Activations Density 0.154%

keywords and headings related to acknowledgments or notices in structured documents

No Comments

No Known Activations