INDEX

Explanations

instances of the word "ca" or its variations that pertain to calcium in scientific contexts

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

GIVEREF

-0.81

 hond

-0.69

 Hond

-0.61

 trasero

-0.61

}\|

-0.60

}},

-0.58

Aloha

-0.58

 tiế

-0.58

}}

-0.58

انت

-0.58

POSITIVE LOGITS

Ca

2.08

ca

1.96

Ca

1.95

CA

1.76

ca

1.68

CA

1.61

 Cahill

1.54

 Caine

1.45

 Caul

1.37

calcium

1.34

Activations Density 0.060%

instances of the word "ca" or its variations that pertain to calcium in scientific contexts

No Comments

No Known Activations