INDEX

Explanations

constructs related to collaborative processes or contributions

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

Text after "by" or a comma

np_acts-logits-general · gemini-2.0-flash

by

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

läge

-0.54

aner

-0.52

 polaire

-0.52

 StringTokenizer

-0.52

waitKey

-0.50

 sanitaires

-0.49

eclamp

-0.49

enosti

-0.48

npos

-0.47

 Wegen

-0.47

POSITIVE LOGITS

ViewImports

0.86

就可以

0.67

 الرياضيه

0.67

就能

0.66

ArrowToggle

0.65

webElementXpaths

0.61

</tfoot>

0.58

 able

0.58

]--;

0.57

 BoxFit

0.55

Activations Density 0.264%

constructs related to collaborative processes or contributions

Text after "by" or a comma

by

No Comments

No Known Activations