INDEX

Explanations

specific medical terms and phrases associated with clinical studies and patient conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

getMinutes

-0.46

extAlignment

-0.43

DebuggerNonUser

-0.43

sko

-0.42

 توم

-0.41

","");

-0.39

Zw

-0.38

unächst

-0.37

adem

-0.37

</

-0.36

POSITIVE LOGITS

+:+

0.96

 EconPapers

0.87

RenderAtEndOf

0.79

InputBorder

0.77

 године

0.74

RegistryLite

0.73

ագրություններ

0.73

Espèce

0.69

Efq

0.68

énario

0.68

Activations Density 0.906%

specific medical terms and phrases associated with clinical studies and patient conditions

No Comments

No Known Activations