INDEX

Explanations

method calls related to action events

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

Java actionPerformed event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

($__

-0.47

 ſta

-0.46

FromNib

-0.42

ngua

-0.42

 pytest

-0.42

<%@

-0.42

DOCTYPE

-0.41

 caviar

-0.40

 Cili

-0.40

 queſta

-0.40

POSITIVE LOGITS

 actionPerformed

4.88

ActionPerformed

1.56

 mouseClicked

1.18

 ActionListener

0.83

ActionListener

0.82

ActionEvent

0.79

setOnAction

0.69

 onOptions

0.67

 onItemClick

0.65

CloseOperation

0.60

Activations Density 0.000%

method calls related to action events

Java actionPerformed event handling

No Comments

No Known Activations