INDEX

Explanations

words related to data organization and structure, particularly in programming and statistics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

帖最后由

-0.50

webgl

-0.45

Bibliograf

-0.45

Ecotoxicity

-0.44

ClientSize

-0.43

}),

-0.43

 parseFrom

-0.43

 giuri

-0.42

urlpatterns

-0.42

POSITIVE LOGITS

 الحره

0.92

󠁮

0.84

 كومونز

0.71

ViewImports

0.70

chtenstein

0.68

󠁣

0.67

thodon

0.67

MLLoader

0.67

 متعلقه

0.66

دانشنامهٔ

0.66

Activations Density 1.510%

words related to data organization and structure, particularly in programming and statistics

No Comments

No Known Activations