INDEX

Explanations

terms related to medical treatments and their effects

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

 CreateTagHelper

-0.87

IntoConstraints

-0.77

 referenties

-0.69

تقاوى

-0.68

TestingModule

-0.65

InitVars

-0.64

openConnection

-0.64

endphp

-0.63

 cherchés

-0.62

存于互联网档案馆

-0.58

POSITIVE LOGITS

 кӀ

0.52

 Amit

0.49

bu

0.48

paz

0.48

 prad

0.48

az

0.47

 amit

0.46

 administrativos

0.46

 cele

0.46

zo

0.46

Activations Density 0.854%

terms related to medical treatments and their effects

No Comments

No Known Activations