INDEX

Explanations

JavaScript and DOM manipulation-related terms

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

System calls or system-related code

np_acts-logits-general · gemini-2.0-flash

system objects and methods

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ReusableCell

-0.74

liceerd

-0.68

 متعلقه

-0.65

ThroughAttribute

-0.61

évaluateur

-0.60

Parcelize

-0.60

SourceChecksum

-0.60

tagHelperRunner

-0.59

 ModelExpression

-0.59

 surla

-0.57

POSITIVE LOGITS

stdlib

0.47

getRuntime

0.43

 useRouter

0.43

 useHistory

0.42

cstdlib

0.40

 government

0.40

 Constitution

0.39

 MediaQuery

0.38

StatusBar

0.37

stdout

0.36

Activations Density 0.201%

JavaScript and DOM manipulation-related terms

System calls or system-related code

system objects and methods

No Comments

No Known Activations