INDEX

Explanations

programming constructs and keywords related to functional operations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 AssemblyCulture

-0.91

CloseOperation

-0.69

SharedDtor

-0.64

 Roskov

-0.63

 queſta

-0.62

🟤

-0.61

 betweenstory

-0.61

 Paglinawan

-0.60

OptionsMenu

-0.59

atguigu

-0.58

POSITIVE LOGITS

tslib

0.39

}());

0.36

 male

0.34

tsx

0.33

"__

0.31

 {}));

0.31

showthread

0.30

‘

0.30

awaiter

0.29

 Magic

0.29

Activations Density 0.161%

programming constructs and keywords related to functional operations in code

No Comments

No Known Activations