INDEX

Explanations

references to signs and displays that convey information or messages

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

StoryboardSegue

-0.87

AndEndTag

-0.67

مصادر

-0.60

 getItemId

-0.55

 kaynağından

-0.55

 XCTest

-0.54

RepeatedField

-0.53

 centrifuged

-0.53

ObjectContext

-0.53

openConnection

-0.52

POSITIVE LOGITS

 signage

1.59

 Signage

1.35

 signs

1.34

 sign

1.33

 billboard

1.32

 billboards

1.30

 Signs

1.20

 banners

1.18

Signs

1.15

signs

1.15

Activations Density 0.175%

references to signs and displays that convey information or messages

No Comments

No Known Activations