INDEX

Explanations

terms related to medical classifications and treatments

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

:✨

-0.87

الحياه

-0.83

StructEnd

-0.79

tonode

-0.74

 kasarigan

-0.74

 ivelany

-0.72

🎰

-0.71

Хьажоргаш

-0.70

sizeCache

-0.70

didSet

-0.65

POSITIVE LOGITS

typec

0.52

 houſe

0.51

 sandero

0.50

BrowserModule

0.49

เอง

0.49

Vgl

0.48

 stessa

0.48

 Diſ

0.47

に限

0.46

 stesso

0.46

Activations Density 1.605%

terms related to medical classifications and treatments

No Comments

No Known Activations