INDEX

Explanations

references to offers and offerings, typically in a commercial or service context

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

offer some

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

PreExecute

-0.37

 Ludwig

-0.36

currentThread

-0.35

 divulgação

-0.35

 computador

-0.35

Scientific

-0.34

NSNotification

-0.34

 INTO

-0.34

 Ritter

-0.34

 pygame

-0.34

POSITIVE LOGITS

 Offer

1.11

Offer

1.00

offer

0.94

 OFFER

0.91

 offer

0.90

offers

0.89

offering

0.86

offered

0.86

 Offered

0.85

Offered

0.85

Activations Density 0.033%

references to offers and offerings, typically in a commercial or service context

offer some

No Comments

No Known Activations