INDEX

Explanations

words related to medical and biological procedures

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

 estekak

-0.72

 препратки

-0.71

期刊论文

-0.71

OGND

-0.70

 تضيفلها

-0.69

ViewInit

-0.67

 arşivlendi

-0.66

 defaultstate

-0.66

PropertyGroup

-0.65

Hentet

-0.65

POSITIVE LOGITS

意

0.51

ak

0.44

rel

0.42

yle

0.41

::$

0.39

 jelent

0.39

ap

0.38

 List

0.38

uti

0.38

 Pred

0.38

Activations Density 0.218%

words related to medical and biological procedures

No Comments

No Known Activations