INDEX

Explanations

phrases and questions related to preferences, choices, and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 autorytatywna

-0.77

 correctes

-0.77

 оригіналу

-0.74

 Administrativna

-0.73

########.

-0.69

ensement

-0.68

VIAF

-0.68

 ویکی‌پدی

-0.67

 insuffisamment

-0.67

 ivelany

-0.67

POSITIVE LOGITS

stateProvider

0.55

0.49

?[

0.47

 fuck

0.44

ographically

0.44

 opinion

0.42

 packing

0.42

Tikang

0.42

or

0.42

 feel

0.41

Activations Density 0.203%

phrases and questions related to preferences, choices, and recommendations

No Comments

No Known Activations