INDEX

Explanations

metadata and headers related to content types and parameters in a document

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

Code snippets with headers/metadata

np_acts-logits-general · gemini-2.0-flash

code and markup attributes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Audiodateien

-0.64

webElement

-0.54

μφωνα

-0.49

cookieParser

-0.47

OGND

-0.47

혔

-0.45

abestanden

-0.45

 sinon

-0.45

Legături

-0.45

ধ্য

-0.44

POSITIVE LOGITS

 Мексичка

0.66

UserScript

0.65

XmlAccessType

0.64

)++;

0.62

IsContent

0.62

exitRule

0.59

complexContent

0.57

httphttps

0.57

byr

0.56

webElementXpaths

0.56

Activations Density 0.223%

metadata and headers related to content types and parameters in a document

Code snippets with headers/metadata

code and markup attributes

No Comments

No Known Activations