INDEX

Explanations

references to accessibility in various contexts

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

accessibility and permeability

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 informée

-0.67

WebServlet

-0.56

CloseOperation

-0.56

WaitGroup

-0.52

bootstrapcdn

-0.50

SourceChecksum

-0.50

OutputType

-0.50

DeleteBehavior

-0.49

ImageContext

-0.49

thâu

-0.48

POSITIVE LOGITS

 Accessibility

1.97

 accessibility

1.88

Accessibility

1.83

accessibility

1.76

acces

0.90

 Accessible

0.89

 Acces

0.87

 inacces

0.84

Acces

0.82

accessible

0.76

Activations Density 0.006%

references to accessibility in various contexts

accessibility and permeability

No Comments

No Known Activations