INDEX

Explanations

terms related to medical research and treatment outcomes involving disease progression and immune response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Roskov

-0.42

<bos>

-0.40

 boek

-0.40

пе

-0.39

+#+

-0.38

 通販

-0.37

↵↵

-0.37

Lähteet

-0.37

 sista

-0.37

 pulumi

-0.37

POSITIVE LOGITS

elemField

0.87

出版年

0.85

 فريبيس

0.79

IsContent

0.79

AccessorTable

0.79

 therefrom

0.76

tagHelperRunner

0.72

IndentedString

0.71

 pageContext

0.70

etheless

0.69

Activations Density 0.208%

terms related to medical research and treatment outcomes involving disease progression and immune response

No Comments

No Known Activations