INDEX

Explanations

HTML list elements

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

nested unordered lists

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

 AssemblyCompany

-0.57

RenderAtEndOf

-0.57

يكب

-0.53

 Infórmanos

-0.52

 betweenstory

-0.52

 насељу

-0.51

 ivelany

-0.49

InjectAttribute

-0.49

addCriterion

-0.47

 iconTwitter

-0.46

POSITIVE LOGITS

JMenu

0.42

ViewInit

0.37

addPreferredGap

0.36

 submenu

0.34

Pro

0.34

 North

0.34

ultar

0.34

lan

0.33

sub

0.33

Aer

0.33

Activations Density 0.019%

HTML list elements

nested unordered lists

No Comments

No Known Activations