INDEX

Explanations

mentions of the term "mega" and its variations in context, indicating a focus on large-scale concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DialogContent

-0.62

 Umum

-0.58

cshtml

-0.58

rrggbb

-0.56

IBinder

-0.56

katkan

-0.55

 InputDecoration

-0.54

 supérieure

-0.54

 preocupes

-0.53

toed

-0.51

POSITIVE LOGITS

 mega

1.01

meg

1.00

 Mega

0.99

Meg

0.89

Mega

0.87

 MEGA

0.86

 megal

0.85

Meg

0.84

watt

0.78

 Megal

0.74

Activations Density 0.086%

mentions of the term "mega" and its variations in context, indicating a focus on large-scale concepts or entities

No Comments

No Known Activations