INDEX

Explanations

references to children and hierarchical structures in code or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ItemBackground

-0.83

 Мексичка

-0.77

mybatisplus

-0.74

Хьажоргаш

-0.68

 GenerationType

-0.66

 BorderRadius

-0.66

Personendaten

-0.63

<bos>

-0.62

PreferredItem

-0.60

 himſelf

-0.60

POSITIVE LOGITS

serviceWorker

0.58

inner

0.58

RectangleBorder

0.58

writerow

0.58

tabular

0.56

 selfie

0.54

 Brat

0.54

 CreateTagHelper

0.54

 depic

0.53

PageFactory

0.53

Activations Density 0.018%

references to children and hierarchical structures in code or data

No Comments

No Known Activations