INDEX

Explanations

medical terminology related to safety and clinical trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Jereo

-0.73

المناصب

-0.64

mobileqq

-0.62

 nakalista

-0.59

rícula

-0.59

 pinulongan

-0.58

 objectAtIndex

-0.58

Хьажоргаш

-0.57

WriteBarrier

-0.57

onCreate

-0.55

POSITIVE LOGITS

 NgModule

0.60

 برانيه

0.57

 estimés

0.55

 potret

0.53

berdayakan

0.48

)))));

0.47

esModule

0.46

enterOuterAlt

0.46

chaun

0.46

<bos>

0.45

Activations Density 0.398%

medical terminology related to safety and clinical trials

No Comments

No Known Activations