INDEX

Explanations

references to programming structures and components related to application configuration and management

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

code identifiers and constructs

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

uvres

-0.56

 étoit

-0.52

 ucapnya

-0.51

berdayakan

-0.50

 plufieurs

-0.49

 poème

-0.49

__":

-0.48

ijiet

-0.48

 Keuangan

-0.48

antaranya

-0.47

POSITIVE LOGITS

 виправивши

0.65

 NUKAT

0.49

 autorytatywna

0.47

 GoogleFonts

0.46

PRWEB

0.46

Hentet

0.44

mapStateToProps

0.43

bewerken

0.43

Pranala

0.43

 للاسماء

0.43

Activations Density 0.003%

references to programming structures and components related to application configuration and management

code identifiers and constructs

No Comments

No Known Activations