INDEX

Explanations

punctuation marks used to denote emotions or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 disambiguazione

-1.04

 للمعارف

-0.95

 resourceCulture

-0.90

 ExecuteAsync

-0.88

AndEndTag

-0.84

expandindo

-0.83

SharedDtor

-0.79

 تانيه

-0.75

 فريبيس

-0.75

下载附件

-0.74

POSITIVE LOGITS

1.07

0.85

0.72

-)

0.72

0.70

))

0.69

0.65

).

0.63

(.

0.62

::

0.61

Activations Density 0.189%

punctuation marks used to denote emotions or expressions

No Comments

No Known Activations