INDEX

Explanations

specific formatting and layout properties in code snippets, particularly related to dimensions and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 EconPapers

-0.65

Jereo

-0.51

ItemBackground

-0.50

RegistryLite

-0.50

addCriterion

-0.50

 geslacht

-0.48

RequestMapping

-0.47

 paroisse

-0.46

 факт

-0.46

iornamento

-0.45

POSITIVE LOGITS

sizeCache

0.67

AnchorTagHelper

0.64

 onCreateView

0.60

ună

0.57

ύπ

0.55

 Kalyan

0.55

jsonwebtoken

0.55

 CGSize

0.54

sizeof

0.54

 Tôi

0.53

Activations Density 0.077%

specific formatting and layout properties in code snippets, particularly related to dimensions and positions

No Comments

No Known Activations