INDEX

Explanations

terms related to diagnostic tests and their results

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ReusableCell

-0.77

 ujednoznacz

-0.72

orteur

-0.71

évaluateur

-0.68

GEBURTSDATUM

-0.68

DockStyle

-0.65

 урна

-0.64

RenderAtEndOf

-0.63

AutoScaleMode

-0.61

AndroidJUnit

-0.59

POSITIVE LOGITS

 serum

0.96

 blood

0.94

 levels

0.86

 Serum

0.84

Serum

0.78

serum

0.76

blood

0.76

 Blood

0.76

Blood

0.75

 BLOOD

0.72

Activations Density 1.026%

terms related to diagnostic tests and their results

No Comments

No Known Activations