INDEX

Explanations

terms related to slipping and sliding actions or situations

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

AndEndTag

-0.88

AxisAlignment

-0.75

MemoryWarning

-0.74

ContentAsync

-0.68

 EdgeInsets

-0.68

endphp

-0.67

 kasarigan

-0.66

 فريبيس

-0.65

 تضيفلها

-0.64

viewDidLoad

-0.63

POSITIVE LOGITS

 slide

0.92

 slides

0.92

 Sliding

0.86

 sliding

0.83

 Slip

0.83

 SLIP

0.81

 Slide

0.80

 Slides

0.78

slip

0.78

slides

0.78

Activations Density 0.145%

terms related to slipping and sliding actions or situations

No Comments

No Known Activations