INDEX

Explanations

numerical data or values related to items or categories

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

invention relates to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MENAFN

-0.60

 CanadaChoose

-0.58

providedIn

-0.56

richTextPanel

-0.50

Collegamenti

-0.44

DockStyle

-0.43



-0.42

+#+

-0.40

Ges

-0.40

Gifts

-0.40

POSITIVE LOGITS

ReusableCell

0.41

UTUP

0.41

 Inventors

0.40

AnimationsModule

0.38

 Ejecutivo

0.38

 dalamnya

0.38

 gevolg

0.38

️⃣

0.37

 maravilla

0.36

odiment

0.36

Activations Density 0.005%

numerical data or values related to items or categories

invention relates to

No Comments

No Known Activations