INDEX

Explanations

mathematical symbols and variables used in equations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

makeConstraints

-0.84

 couvert

-0.73

Sti

-0.72

esus

-0.71

ReusableCell

-0.71

็จ

-0.71

BTN

-0.71

vzd

-0.71

 dand

-0.70

sstream

-0.70

POSITIVE LOGITS

 alpha

1.95

alpha

1.82

 Alpha

1.77

α

1.69

Alpha

1.68

 ALPHA

1.53

ALPHA

1.46

α

1.45

alph

1.27

アルファ

1.24

Activations Density 0.091%

mathematical symbols and variables used in equations

No Comments

No Known Activations