INDEX

Explanations

categories and types related to medical conditions, specifically differentiating between types of fraud and health-related conditions

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

after types/kinds/both/including

np_acts-logits-general · gemini-2.0-flash

types and kinds

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

 Manif

-0.56

 aliens

-0.52

avigation

-0.51

 soundness

-0.50

 pamph

-0.50

Manif

-0.49

:+:

-0.47

 Dionys

-0.47

avelmente

-0.47

 dazu

-0.46

POSITIVE LOGITS

 types

0.75

 Types

0.73

Types

0.72

Tipos

0.67

 tipos

0.67

 jenis

0.66

types

0.66

 type

0.64

 النوع

0.63

 TYPES

0.63

Activations Density 0.938%

categories and types related to medical conditions, specifically differentiating between types of fraud and health-related conditions

after types/kinds/both/including

types and kinds

No Comments

No Known Activations