INDEX

Explanations

numerical values, especially those relating to quantities or measurements

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

numbers and quantities

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

RegressionTest

-0.74

ViewImports

-0.69

 يتيمه

-0.64

点此举报

-0.59

adaptiveStyles

-0.59

 CanadaChoose

-0.57

 betweenstory

-0.51

 Autorizaciones

-0.50

 nonUne

-0.50

 صوتيه

-0.49

POSITIVE LOGITS

WireFormatLite

0.43

 kasarigan

0.43

 ویکی‌پدیا

0.42

 yoksa

0.36

InteropServices

0.31

 traditionnelle

0.31

 MainAxisSize

0.31

VolleyError

0.31

getFullYear

0.29

Nix

0.29

Activations Density 0.075%

numerical values, especially those relating to quantities or measurements

numbers and quantities

No Comments

No Known Activations