INDEX

Explanations

elements and their structure in a markup or programming language syntax

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

XML or code tags/attributes

np_acts-logits-general · gemini-2.0-flash

variable names and identifiers

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ChildScrollView

-0.55

AnimationsModule

-0.50

 protoimpl

-0.48

RTCF

-0.45

enumii

-0.43

 مشين

-0.43

 surla

-0.43

principalTable

-0.40

帖最后由

-0.40

GroupLayout

-0.39

POSITIVE LOGITS

 useParams

0.68

 getItemId

0.64

 getId

0.56

idUser

0.54

 uuidv

0.52

GeneratedValue

0.52

HostException

0.51

号码

0.51

ID

0.50

ids

0.50

Activations Density 0.790%

elements and their structure in a markup or programming language syntax

XML or code tags/attributes

variable names and identifiers

No Comments

No Known Activations