INDEX

Explanations

mathematical symbols and variables used in equations and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

枝

-0.57

вку

-0.55

 COMPUT

-0.54

pogon

-0.51

Slf

-0.51

thorpe

-0.50

 FOOT

-0.48

rel

-0.46

chuhe

-0.46

 CALCUL

-0.46

POSITIVE LOGITS

 BoxDecoration

0.97

 يتيمه

0.94

 tfsi

0.88

."]

0.87

 becauſe

0.86

 myſelf

0.85

RectangleBorder

0.85

 Chriftian

0.83

"]]

0.82

 Majefty

0.81

Activations Density 1.449%

mathematical symbols and variables used in equations and definitions

No Comments

No Known Activations