INDEX

Explanations

descriptions of devices and their applications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Personendaten

-0.59

</strong>

-0.55

RectangleBorder

-0.52

 mutually

-0.50

RetentionPolicy

-0.49

]-->

-0.48

 саны

-0.47

 kív

-0.45

 locura

-0.45

Intérieur

-0.44

POSITIVE LOGITS

SharedCtor

0.79

Autoritní

0.59

tahui

0.56

orari

0.56

voici

0.54

 flats

0.53

phosa

0.52

ircraft

0.52

NLI

0.52

KDE

0.51

Activations Density 0.525%

descriptions of devices and their applications in various contexts

No Comments

No Known Activations