INDEX

Explanations

numerical data and related symbols, especially in a structured format like a table

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ollectionView

-0.61

 Weeks

-0.61

AttributeSet

-0.58

GOTREF

-0.56

Options

-0.54

jenner

-0.53

flush

-0.53

esgue

-0.53

úgó

-0.52

//

-0.51

POSITIVE LOGITS

 betweenstory

0.68

InjectAttribute

0.67

 beginnetje

0.60

 autorytatywna

0.60

يكب

0.59

 externi

0.59

Hochspringen

0.59

 مرئيه

0.58

Спасылкі

0.57

 typelib

0.56

Activations Density 0.408%

numerical data and related symbols, especially in a structured format like a table

No Comments

No Known Activations