INDEX

Explanations

elements related to structured data or configuration settings

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

Code or file-related text

np_acts-logits-general · gemini-2.0-flash

HTML, code, XML

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.79

AndEndTag

-0.78

MigrationBuilder

-0.72

хьтан

-0.71

astify

-0.71

 AttributeSet

-0.69

ImageContext

-0.69

 kasarigan

-0.67

 nahilalakip

-0.66

 Wikimedijinoj

-0.65

POSITIVE LOGITS

aarrggbb

0.30

愷

0.30

 nacer

0.30

 corriendo

0.28

 cuartos

0.27

미

0.26

 sentía

0.25

 מי

0.25

 seguía

0.24

 libremente

0.24

Activations Density 0.441%

elements related to structured data or configuration settings

Code or file-related text

HTML, code, XML

No Comments

No Known Activations