INDEX

Explanations

phrases related to medical assessments or preventive measures

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

PagerAdapter

-0.65

Rie

-0.61

WebServlet

-0.57

 pairs

-0.54

[:,

-0.53

Ste

-0.51

teis

-0.51

appar

-0.50

 गए

-0.50

Lap

-0.50

POSITIVE LOGITS

 make

0.90

 help

0.89

 uſe

0.83

 للمعارف

0.83

 create

0.83

 build

0.81

 mobilize

0.80

PerformLayout

0.80

 eliminate

0.78

 shave

0.78

Activations Density 0.239%

phrases related to medical assessments or preventive measures

No Comments

No Known Activations