INDEX

Explanations

references to medical settings or legal systems concerning penalties and practices

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

aarrggbb

-0.94

verwijspagina

-0.92

DockStyle

-0.90

 kasarigan

-0.88

StructEnd

-0.87

 المعيارى

-0.83

 NSCoder

-0.82

LayoutConstraint

-0.81

rungsseite

-0.78

AddHtmlAttribute

-0.78

POSITIVE LOGITS

 begin

1.62

begin

1.37

 Begin

1.23

Begin

1.22

 first

1.16

 begins

1.16

 beginning

1.15

 began

1.15

 BEGIN

1.14

first

1.00

Activations Density 0.177%

references to medical settings or legal systems concerning penalties and practices

No Comments

No Known Activations