INDEX

Explanations

technical terms and features related to software and application integration

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

"including," "with," "in," or similar list introductions

np_acts-logits-general · gemini-2.0-flash

features and capabilities

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

Portale

-0.77

sizeCache

-0.71

 Initialise

-0.69

WebVitals

-0.66

 AppModule

-0.65

ActionCreators

-0.64

 desorption

-0.63

 considéré

-0.62

 myſelf

-0.62

 chofe

-0.62

POSITIVE LOGITS

 auto

0.88

 features

0.82

 ability

0.79

 Auto

0.77

 automatic

0.73

 customizable

0.73

 built

0.73

 automatically

0.68

 feature

0.68

 multiple

0.67

Activations Density 0.331%

technical terms and features related to software and application integration

"including," "with," "in," or similar list introductions

features and capabilities

No Comments

No Known Activations