INDEX

Explanations

references to programming components and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyTitle

-1.15

contentLoaded

-0.90

IndentedString

-0.85

AddTagHelper

-0.81

InjectAttribute

-0.79

rrggbb

-0.78

 AssemblyCulture

-0.78

:✨

-0.76

 InputDecoration

-0.75

featureID

-0.74

POSITIVE LOGITS

protoc

0.70

FormTagHelper

0.70

<?>

0.65

RenderAtEndOf

0.59

ⓧ

0.59

 Component

0.58

 JPanel

0.57

WebServlet

0.57

yecek

0.52

blogspot

0.52

Activations Density 0.032%

references to programming components and errors

No Comments

No Known Activations