INDEX

Explanations

structured data or lists related to specific topics

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

list, schematic, or product information

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

IsMutable

-0.69

 autorytatywna

-0.68

fjspx

-0.66

 estekak

-0.63

Rüyada

-0.61

archiviato

-0.57

tagHelperRunner

-0.54

 ویکی‌پدی

-0.54

AutoScaleMode

-0.52

 propOrder

-0.52

POSITIVE LOGITS

 betweenstory

0.44

IUrlHelper

0.41

 htons

0.37

 projectId

0.35

OfMonth

0.35

 getattr

0.34

ohs

0.34

Mesa

0.33

 Torr

0.33

Connector

0.33

Activations Density 0.003%

structured data or lists related to specific topics

list, schematic, or product information

No Comments

No Known Activations