INDEX

Explanations

mathematical notations and symbols, particularly those associated with equations and inequalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

CrossRef

-0.73

AutoScale

-0.71

 Cass

-0.70

 cass

-0.69

 Wiktionnaire

-0.67

 endforeach

-0.66

 Kirke

-0.65

viewDidLoad

-0.65

 surla

-0.65

 indisponible

-0.64

POSITIVE LOGITS

 esquerdo

0.78

findElement

0.67

newBuilder

0.67

لاثة

0.64

</em>

0.62

 Budd

0.60

 Gusto

0.59

<em>

0.59

ghalaya

0.58

Activations Density 0.434%

mathematical notations and symbols, particularly those associated with equations and inequalities

No Comments

No Known Activations