INDEX

Explanations

references to maps and navigation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 resourceCulture

-0.61

artifactId

-0.59

 regardant

-0.59

principalColumn

-0.58

AddHtmlAttribute

-0.56

Personensuche

-0.54

IBOutlet

-0.53

нент

-0.51

bpy

-0.51

 Whilst

-0.50

POSITIVE LOGITS

 maps

2.50

map

2.40

 Maps

2.20

Map

2.04

 mapa

1.85

Maps

1.75

maps

1.71

 MAPS

1.68

 mapped

1.67

 mapas

1.66

Activations Density 0.188%

references to maps and navigation

No Known Activations