INDEX

Explanations

numerical and mathematical symbols or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

-0.72

ÚBL

-0.72

buttonBar

-0.71

Бахар

-0.65

 Paglinawan

-0.61

 تضيفلها

-0.61

utnik

-0.61

amentals

-0.60

ItemBackground

-0.60

endregion

-0.60

POSITIVE LOGITS

ftagPool

0.60

 zelfs

0.52

 dokonce

0.50

 keç

0.48

XMLSchema

0.48

 addirittura

0.48

 acoper

0.48

ManagedBean

0.47

 jopa

0.47

 विश्वसनीयता

0.46

Activations Density 1.225%

numerical and mathematical symbols or structures

No Comments

No Known Activations