INDEX

Explanations

references to scientific models and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

\}}

-0.45

 الاطلاع

-0.43

iget

-0.41

 onItemClick

-0.41

 Rend

-0.40

.".

-0.38

}\}

-0.38

 aproximativ

-0.38

 Pokies

-0.38

 ModelExpression

-0.37

POSITIVE LOGITS

 Infórmanos

0.64

 Theſe

0.64

 uſed

0.63

MLLoader

0.62

 myſelf

0.61

RegressionTest

0.60

’

0.60

sidemargin

0.60

RegistryLite

0.59

 Monfieur

0.59

Activations Density 0.536%

references to scientific models and variables

No Comments

No Known Activations