INDEX

Explanations

mathematical symbols and notation for expressions related to advanced equations and inequalities in statistics or mathematics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Latimer

-0.71

 Driscoll

-0.69

 Larkin

-0.68

 chantier

-0.68



-0.68

 Faktor

-0.67

tedt

-0.65

ات

-0.65



-0.63

 Wheeler

-0.63

POSITIVE LOGITS

)^{-

1.24

]^{-

1.15

}^{-

1.09

^{-

1.04

RefNanny

1.02

^{-

0.92

 }^{-

0.90

SequentialGroup

0.87

Ba

0.86

[::-

0.86

Activations Density 0.358%

mathematical symbols and notation for expressions related to advanced equations and inequalities in statistics or mathematics

No Comments

No Known Activations