INDEX

Explanations

references to medical conditions and diagnostic categories

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

Numerical data in tables

np_acts-logits-general · gemini-2.0-flash

0.0

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

+#+#

-0.77

mybatisplus

-0.74

 للمعارف

-0.69

yntaxException

-0.67

 Paglinawan

-0.65

 ivelany

-0.62

Бахар

-0.62

ArgsConstructor

-0.62

KommentareTeilen

-0.59

PhysRev

-0.58

POSITIVE LOGITS

ThroughAttribute

0.48

://

0.45

غب

0.45

nsic

0.43

 MonoBehaviour

0.43

 auszu

0.43

protoimpl

0.42

#+#

0.42

ngen

0.41

legung

0.41

Activations Density 0.399%

references to medical conditions and diagnostic categories

Numerical data in tables

0.0

No Comments

No Known Activations