INDEX

Explanations

occurrences of numerical values or parameters

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

autorest.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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

adaptiveStyles

-0.57

Personendaten

-0.54

exitRule

-0.54

AddHtmlAttribute

-0.54

envolvimento

-0.48

 Rost

-0.47

蹟

-0.47

 marito

-0.45

">';

-0.45

stateProvider

-0.45

POSITIVE LOGITS

GraphicsUnit

0.96

 تضيفلها

0.88

httphttps

0.75

IntoConstraints

0.71

FundMe

0.63

 MessageBoxIcon

0.61

chery

0.59

 Thesaurus

0.57

ochrom

0.57

GenerationType

0.57

Activations Density 0.001%

occurrences of numerical values or parameters

autorest.By

No Comments

No Known Activations