INDEX

Explanations

medical terminology related to specific health conditions and their treatments

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

"case" or "cases" followed by a description

np_acts-logits-general · gemini-2.0-flash

reporting novel cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

#+#

-0.76

клопе

-0.65

 AssemblyCulture

-0.65

 مرئيه

-0.61

ändler

-0.61

IsContent

-0.60

CompilerServices

-0.58

 MonoBehaviour

-0.57

huevos

-0.57

 Dumbledore

-0.56

POSITIVE LOGITS

 cases

1.92

 case

1.79

 Cases

1.62

 patients

1.59

cases

1.56

case

1.50

 Case

1.49

Cases

1.48

 patient

1.48

Case

1.47

Activations Density 1.101%

medical terminology related to specific health conditions and their treatments

"case" or "cases" followed by a description

reporting novel cases

No Comments

No Known Activations