INDEX

Explanations

mathematical notations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 المعيارى

-1.04

XmlAccessorType

-0.96

rrggbb

-0.96

elemField

-0.92

DockStyle

-0.89

BeginContext

-0.86

 ویکی‌پدی

-0.86

expandindo

-0.84

extAlignment

-0.81

Grit

-0.78

POSITIVE LOGITS

0.83

<blockquote>

0.71

 <<<<<<<<<<<<<<

0.66

0.58

 evid

0.53

mtd

0.52

itemName

0.51

 least

0.51

 sides

0.51

nál

0.50

Activations Density 0.152%

mathematical notations and symbols

No Comments

No Known Activations