INDEX

Explanations

references to specific programming classes and methods within a framework

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

after "Monolog", "Doctrine", or "Controller"

np_acts-logits-general · gemini-2.0-flash

logs, namespaces, and classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.73

migrationBuilder

-0.47

 AssemblyTitle

-0.45

 <=",

-0.44

stateParams

-0.41

ркут

-0.41

CharStream

-0.41

 CallOverrides

-0.40

ForRow

-0.39

 droit

-0.39

POSITIVE LOGITS

MLLoader

0.86

0.80

+#+

0.77

 himſelf

0.67

#+#

0.66

 myſelf

0.66

 Reſ

0.64

 themſelves

0.64

\*

0.63

esgue

0.63

Activations Density 0.049%

references to specific programming classes and methods within a framework

after "Monolog", "Doctrine", or "Controller"

logs, namespaces, and classes

No Comments

No Known Activations