INDEX

Explanations

sections of text that contain legal or structured document formats

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

paragraph numbers

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

GEBURTSDATUM

-0.99

OGND

-0.89

 queſta

-0.84

 שוליים

-0.83

 مرئيه

-0.82

IUrlHelper

-0.77

 pinulongan

-0.77

 ویکی‌پدی

-0.76

 kasarigan

-0.74

 للاسماء

-0.73

POSITIVE LOGITS

The

0.48

Though

0.43

Regarding

0.40

Although

0.39

According

0.39

One

0.39

There

0.38

Unlike

0.37

In

0.36

The

0.36

Activations Density 0.029%

sections of text that contain legal or structured document formats

paragraph numbers

No Comments

No Known Activations