INDEX

Explanations

elements and attributes often used in programming or data representation

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

Code-related tokens

np_acts-logits-general · gemini-2.0-flash

winning dress analysis

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 disponibilités

-0.37

StackNavigator

-0.32

ContentLoaded

-0.32

rophi

-0.31

 continuum

-0.31

Find

-0.30

rhy

-0.30

gin

-0.29

 Gino

-0.29

લા

-0.29

POSITIVE LOGITS

 فريبيس

0.83

 AssemblyProduct

0.69

 proprement

0.62

MigrationBuilder

0.61

 AssemblyVersion

0.59

IsContent

0.59

0.58

 ComVisible

0.56

UpInside

0.55

tanleria

0.54

Activations Density 0.684%

elements and attributes often used in programming or data representation

Code-related tokens

winning dress analysis

No Comments

No Known Activations