INDEX

Explanations

terms and phrases related to standards and standardization in various contexts

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

"Standard" followed by "of" or a statistical term

np_acts-logits-general · gemini-2.0-flash

standard of, deviation, error

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyTitle

-0.92

WriteLiteral

-0.64

 CreateTagHelper

-0.64



-0.64

 useEffect

-0.63

omitempty

-0.63

 convertView

-0.62

 hostages

-0.62

assins

-0.62

RESOLVED

-0.61

POSITIVE LOGITS

StandardCharsets

0.99

 STANDARD

0.93

 deviation

0.89

 Standard

0.87

STANDARD

0.86

 standard

0.85

standard

0.83

 Standards

0.81

 standards

0.80

Standard

0.78

Activations Density 0.152%

terms and phrases related to standards and standardization in various contexts

"Standard" followed by "of" or a statistical term

standard of, deviation, error

No Comments

No Known Activations