INDEX

Explanations

programming and file handling terms or concepts

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

Properties, class names, file names, or dialogs

np_acts-logits-general · gemini-2.0-flash

code components and UI elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 <<<<<<<<<<<<<<

-0.61

setopt

-0.56

NUMX

-0.55

outez

-0.55

нрави

-0.55

Crossref

-0.53

abz

-0.52

ⓧ

-0.51

 Référence

-0.51

）』

-0.50

POSITIVE LOGITS

Name

0.71

verwijspagina

0.67

ulario

0.65

isateur

0.63

 المعيارى

0.61

stood

0.59

好

0.58

Than

0.58

cionario

0.57

kadot

0.54

Activations Density 0.202%

programming and file handling terms or concepts

Properties, class names, file names, or dialogs

code components and UI elements

No Comments

No Known Activations