INDEX

Explanations

terms related to healthcare, diagnostics, and medical conditions

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

Followed by words like "standard", "approach," "theme", "work"

np_acts-logits-general · gemini-2.0-flash

keywords followed by categories

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

\{\\

-0.83

oneofs

-0.63

:✨

-0.63

 snippetHide

-0.59

Tembelea

-0.59

AccessorTable

-0.59

CloseOperation

-0.58

rungsseite

-0.58

featureID

-0.56

])))

-0.56

POSITIVE LOGITS

uxxxx

0.60

 Италијани

0.53

ειτουργ

0.52

 approach

0.51

quine

0.51

etera

0.50

 understanding

0.49

AndroidJUnit

0.49

FundMe

0.49

 aspect

0.48

Activations Density 0.553%

terms related to healthcare, diagnostics, and medical conditions

Followed by words like "standard", "approach," "theme", "work"

keywords followed by categories

No Comments

No Known Activations