INDEX

Explanations

terms associated with healthcare and related services

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

Code, file paths, and programming terms

np_acts-logits-general · gemini-2.0-flash

boolean logic and code keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

RegistryLite

-0.85

SharedCtor

-0.59

BeginContext

-0.57

Personendaten

-0.56

"",

-0.54

AfterClass

-0.54

makeConstraints

-0.53

ConstraintMaker

-0.52

Tembelea

-0.52

awtextra

-0.51

POSITIVE LOGITS

 للمعارف

0.84

 FetchType

0.72

UserScript

0.66

providedIn

0.65

buie

0.63

 فريبيس

0.63

 doInBackground

0.62

adpleegd

0.62

guenos

0.61

RectangleBorder

0.61

Activations Density 1.914%

terms associated with healthcare and related services

Code, file paths, and programming terms

boolean logic and code keywords

No Comments

No Known Activations