INDEX

Explanations

references to specific scientific studies or experiments regarding quantum mechanics and entanglement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

testens

-0.41

ONTO

-0.41

iget

-0.41

::-

-0.40

 Rend

-0.39

INSEE

-0.39

 aproximativ

-0.39

RAINT

-0.39

KURZBESCHREIBUNG

-0.38

 ende

-0.38

POSITIVE LOGITS

 Infórmanos

0.71

tagHelperRunner

0.68

Rüyada

0.66

’

0.66

]--;

0.63

 coupable

0.63

nościo

0.60

RegressionTest

0.59

허

0.57

Initializable

0.56

Activations Density 0.663%

references to specific scientific studies or experiments regarding quantum mechanics and entanglement

No Comments

No Known Activations