INDEX

Explanations

JSON-like structured data patterns

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

{:ok, pid} structure

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CloseOperation

-0.65

 surla

-0.64

 Wicidata

-0.57

eira

-0.54

FileInput

-0.53

orianCalendar

-0.52

 jadx

-0.51

omock

-0.49

Tē

-0.49

XmlAccessType

-0.48

POSITIVE LOGITS

stateProvider

0.40

writerow

0.39

AddTagHelper

0.38

reason

0.35

Einzelnachweise

0.35

 sonriente

0.31

 sonrisa

0.30

ReusableCell

0.29

 kaarangay

0.29

 Besøkt

0.29

Activations Density 0.041%

JSON-like structured data patterns

{:ok, pid} structure

No Comments

No Known Activations