INDEX

Explanations

locations related to medical contexts and emergencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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



-0.56

addPreferredGap

-0.53

новниш

-0.52

 online

-0.51

HasForeignKey

-0.50

Legături

-0.48

исленность

-0.48

addCriterion

-0.48

在线

-0.48

WebServlet

-0.48

POSITIVE LOGITS

 walls

0.76

 floor

0.72

 viewDidLoad

0.72

 area

0.71

helves

0.70

osphere

0.64

sbereich

0.63

 wall

0.62

 cavity

0.60

znej

0.59

Activations Density 0.800%

locations related to medical contexts and emergencies

No Comments

No Known Activations