INDEX

Explanations

technical terms related to computer programming and events

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

<start_of_turn> user or Routed<start_of_turn> event args

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

 propOrder

-0.52

abestanden

-0.48

NameInMap

-0.47

WithIOException

-0.47

 للمعارف

-0.46

principalTable

-0.46

 kaarangay

-0.45

WebVitals

-0.45

 Wikimedijinoj

-0.44

uxxxx

-0.44

POSITIVE LOGITS

 RoutedEventArgs

0.76

 Clean

0.44

 cleanliness

0.43

getClassLoader

0.43

bolistas

0.41

 sklep

0.41

addFlags

0.40

 desertcart

0.40

kegaard

0.40

 UITableViewCell

0.40

Activations Density 0.000%

technical terms related to computer programming and events

<start_of_turn> user or Routed<start_of_turn> event args

No Comments

No Known Activations