INDEX

Explanations

technical terms and jargon related to healthcare and treatment methodologies

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

webElementXpaths

-0.65

unknownFields

-0.56

تقاوى

-0.52

 esboço

-0.50

شكرا

-0.50

AutoScaleMode

-0.50

scriptcase

-0.49

GeneratedValue

-0.49

{}",

-0.49

zędu

-0.49

POSITIVE LOGITS

0.81

 متعلقه

0.69

0.67

OGND

0.66

Personensuche

0.62

 kaynağından

0.59

pecu

0.56

*,

0.54

abetes

0.54

**

0.53

Activations Density 0.033%

technical terms and jargon related to healthcare and treatment methodologies

No Comments

No Known Activations