INDEX

Explanations

references to inventions and their descriptions

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_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

-------

-0.49

Билгалдахарш

-0.45

født

-0.43

rungsseite

-0.42

 Fassung

-0.41

Біографія

-0.41

 iconLine

-0.40

 minOccurs

-0.40

 nonatomic

-0.38

Nuorodos

-0.38

POSITIVE LOGITS

 patted

0.55

obach

0.42

 ویکی‌پدی

0.41

 Inform

0.40

 patch

0.40

slo

0.40

lok

0.40

 Beat

0.39

contentPadding

0.39

PATCH

0.39

Activations Density 0.032%

references to inventions and their descriptions

invention relates to

No Comments

No Known Activations