INDEX

Explanations

spatial references related to locations or districts

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

places and specific entities

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

 performance

-0.38

󠁴

-0.35

 size

-0.34

žiai

-0.33

 design

-0.33

 feature

-0.32

 juſt

-0.32

 senta

-0.32

 Ukuran

-0.32

 standing

-0.32

POSITIVE LOGITS

 invokingState

0.66

MigrationBuilder

0.64

Personensuche

0.59

 ModelExpression

0.54

principalColumn

0.53

 مواليد

0.51

 outskirts

0.50

دانشنامهٔ

0.49

 cages

0.49

:+:

0.48

Activations Density 0.016%

spatial references related to locations or districts

places and specific entities

No Comments

No Known Activations