INDEX

Explanations

programming-related terminologies and functions, particularly those associated with events and callbacks

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

hook then, load then, Active Rule

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

onOptions

-0.65

(!__

-0.50

risch

-0.49

ParallelGroup

-0.49

tvguidetime

-0.49

 newOwner

-0.48

DrawerLayout

-0.46

 contextLoads

-0.43

 مرئيه

-0.43

Datuak

-0.42

POSITIVE LOGITS

 trigger

0.54

trigger

0.52

 triggers

0.52

 triggered

0.51

UserScript

0.49

useEffect

0.48

triggers

0.46

ViewInit

0.46

 autom

0.45

stateMutability

0.44

Activations Density 0.053%

programming-related terminologies and functions, particularly those associated with events and callbacks

hook then, load then, Active Rule

No Comments

No Known Activations