INDEX

Explanations

functions and commands associated with data manipulation and configuration settings

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

writing data or code

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

ſy

-0.29

 ſhe

-0.28

有多少

-0.28

 Wings

-0.28

Xna

-0.28

 whoſe

-0.27

BeginInit

-0.26

دانشنامهٔ

-0.26

 fuper

-0.26

andExpect

-0.25

POSITIVE LOGITS

EDEFAULT

0.63

nodoc

0.63

 يتيمه

0.62

 ब्रेकडाउन

0.59

RenderAtEndOf

0.58

 betweenstory

0.57

ftagPool

0.57

 nahilalakip

0.56

ollectionView

0.54

RTEE

0.54

Activations Density 0.013%

functions and commands associated with data manipulation and configuration settings

writing data or code

No Comments

No Known Activations