INDEX

Explanations

subjects related to healthcare management and evidence presentation

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

followed by numbers or letters

np_acts-logits-general · gemini-2.0-flash

numeral, sequence, or heading

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ChildScrollView

-0.86

Personensuche

-0.82

قایناق‌لار

-0.77

 nahilalakip

-0.76

Personendaten

-0.75

хьтан

-0.72

 Roskov

-0.71

 Италијани

-0.71

Хьажоргаш

-0.70

 يتيمه

-0.69

POSITIVE LOGITS

II

1.58

III

1.57

1.48

№

1.30

\#

1.26

IV

1.25

 number

1.23

VII

1.23

 VIII

1.20

 Number

1.16

Activations Density 1.396%

subjects related to healthcare management and evidence presentation

followed by numbers or letters

numeral, sequence, or heading

No Comments

No Known Activations