INDEX

Explanations

references to specific numerical values or identifiers

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

numbers and ordinals

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

WaitGroup

-0.39

<%@

-0.37

atí

-0.35

MultipartFile

-0.35

得

-0.34

 SafeMath

-0.34

ViewImports

-0.33

 StatefulWidget

-0.33

UserScript

-0.33

FieldDescriptor

-0.31

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.65

EndGlobalSection

0.54

styleType

0.51

 CreateTagHelper

0.49

 Autorizaciones

0.48

AddTagHelper

0.47

TEN

0.47

ten

0.47

VersionUID

0.46

Jereo

0.46

Activations Density 0.035%

references to specific numerical values or identifiers

numbers and ordinals

No Comments

No Known Activations