INDEX

Explanations

elements of code related to creating and manipulating web maps

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

before "map" or "maps"

np_acts-logits-general · gemini-2.0-flash

map-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

AddHtmlAttribute

-0.89

posedge

-0.76

 resourceCulture

-0.75

 NgModule

-0.71

+#+#

-0.69

 تضيفلها

-0.69

 GenerationType

-0.67

msgSender

-0.65

 oprot

-0.65

oneofs

-0.64

POSITIVE LOGITS

map

3.79

map

3.41

Map

3.08

Map

2.92

 maps

2.49

MAP

2.31

MAP

2.27

 mapa

2.25

 Maps

2.05

 mappa

2.00

Activations Density 0.174%

elements of code related to creating and manipulating web maps

before "map" or "maps"

map-related concepts

No Comments

No Known Activations