INDEX

Explanations

structural elements in a hierarchical or nested format, likely related to programming or data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

endphp

-0.74

+#+#

-0.72

initializeApp

-0.69

viewDidLoad

-0.68

libft

-0.65

intios

-0.63

DCT

-0.62

 StatelessWidget

-0.62

<eos>

-0.58

 resourceCulture

-0.58

POSITIVE LOGITS

tagHelperRunner

0.51

 Приступљено

0.50

thâu

0.49

kháu

0.49

 produisons

0.48

enschappelijke

0.48

 numerus

0.48

CodedInputStream

0.47

 informée

0.46

好处

0.46

Activations Density 0.256%

structural elements in a hierarchical or nested format, likely related to programming or data representation

No Comments

No Known Activations