INDEX

Explanations

elements related to programming constructs and functional programming syntax

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

Code or math expressions

np_acts-logits-general · gemini-2.0-flash

lens and rule structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uerdo

-0.47

‭

-0.46

 JADX

-0.45

 metav

-0.44

grä

-0.41

 اطلع

-0.41

 potete

-0.41

OCCURRED

-0.41

zzleHttp

-0.40

Bur

-0.40

POSITIVE LOGITS

MigrationBuilder

0.76

 propOrder

0.75

TagMode

0.73

DataAnnotations

0.72

 Normdatei

0.70

 تضيفلها

0.66

setVerticalGroup

0.66

RenderAtEndOf

0.63

beelden

0.62

 memp

0.62

Activations Density 0.282%

elements related to programming constructs and functional programming syntax

Code or math expressions

lens and rule structures

No Comments

No Known Activations