INDEX

Explanations

programming-related terms and functions associated with data structures and event handling

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

code execution

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

 للمعارف

-0.69

extAlignment

-0.67

новниш

-0.64

 مرئيه

-0.63

tonsoft

-0.63

__":

-0.62

IUrlHelper

-0.61

WEBPACK

-0.60

 ͡°

-0.60

__':

-0.60

POSITIVE LOGITS

 which

0.43

vœ

0.39

 equation

0.37

 factors

0.37

 chiffre

0.35

RuleContext

0.35

 whom

0.33

 cours

0.33

úgó

0.32

Activations Density 0.045%

programming-related terms and functions associated with data structures and event handling

code execution

No Comments

No Known Activations