INDEX

Explanations

terms related to medical study protocols and their outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

angliski

-0.52

 worst

-0.49

χος

-0.47

ыре

-0.43

iastes

-0.43

yz

-0.43

ður

-0.42

makeConstraints

-0.42

ruk

-0.41

ums

-0.40

POSITIVE LOGITS

省市镇

0.79

DebuggerNonUser

0.75

UnitTesting

0.73

AndroidJUnit

0.66

 disambiguazione

0.66

 становника

0.65

 Proben

0.64

endphp

0.64

 <=",

0.64

protoimpl

0.63

Activations Density 1.172%

terms related to medical study protocols and their outcomes

No Comments

No Known Activations