INDEX

Explanations

terms related to medical conditions and patient data management

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

Word before "in" indicating a location or organization

np_acts-logits-general · gemini-2.0-flash

names of places and institutions

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

⎨

-0.60

 espirituales

-0.57

 ویکی‌پدیا

-0.57

″]

-0.57

>>();

-0.56

Diweddarwch

-0.54

țiilor

-0.52

))=\

-0.51

»)

-0.51

bbons

-0.51

POSITIVE LOGITS

posables

0.55

OnDelete

0.53

 للاسماء

0.53

ಾರ

0.51

Portale

0.51

Uff

0.50

HasForeignKey

0.49

IBOutlet

0.48

หว่าง

0.47

RenderAtEndOf

0.47

Activations Density 0.314%

terms related to medical conditions and patient data management

Word before "in" indicating a location or organization

names of places and institutions

No Comments

No Known Activations