INDEX

Explanations

terms related to healthcare technology and diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

>`;

-0.59

+#+

-0.57

>--}}

-0.55

WindowConstants

-0.54

 betweenstory

-0.54

mtrl

-0.50

WebElementEntity

-0.48

}}}

-0.48

UserScript

-0.47

>-->

-0.47

POSITIVE LOGITS

RegistryLite

0.52

 Seward

0.52

ISupport

0.50

writeField

0.49

 daarbij

0.47

 pthread

0.47

MemoryWarning

0.46

WriteBarrier

0.46

uctura

0.46

 tjen

0.46

Activations Density 0.573%

terms related to healthcare technology and diagnostics

No Comments

No Known Activations