INDEX

Explanations

references to the Dojo toolkit and related components in programming contexts

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

java persistence framework keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

InstrumentedTest

-0.66

EnableWeb

-0.62

endphp

-0.59

 CURIAM

-0.56

abestanden

-0.52

 MainAxisSize

-0.52

ListItemIcon

-0.52

 ***!

-0.51

EndContext

-0.49

locaust

-0.49

POSITIVE LOGITS

zoom

0.39

webElement

0.38

 crimes

0.38

ibatis

0.36

ViewFeatures

0.36

 zoom

0.35

mybatisplus

0.35

zko

0.35

Zoom

0.35

 desem

0.35

Activations Density 0.005%

references to the Dojo toolkit and related components in programming contexts

java persistence framework keywords

No Comments

No Known Activations