INDEX

Explanations

words indicating time or sequence

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

currently or justsimple or nowjust or thennow or justjust now or then

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

tra

-0.35

Fin

-0.35

thing

-0.35

ार्

-0.34

sizePolicy

-0.31

THING

-0.31

No

-0.30

The

-0.30

scriptcase

-0.30

Se

-0.29

POSITIVE LOGITS

 Infórmanos

0.71

ChildScrollView

0.69

 queſta

0.64

 autorytatywna

0.64

 snippetHide

0.63

 estekak

0.61

DotNetBar

0.58

 saites

0.57

ьаж

0.57

 resourceCulture

0.56

Activations Density 0.128%

words indicating time or sequence

currently or justsimple or nowjust or thennow or justjust now or then

No Comments

No Known Activations