INDEX

Explanations

references to individuals who have held previous positions of power or office

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

 numberOfRows

-0.80

脚注の使い方

-0.79

styleType

-0.78

 disambiguazione

-0.76

HtmlAttribute

-0.74

#+#

-0.71

 épis

-0.70

 InputDecoration

-0.69

 coupable

-0.69

Tembelea

-0.69

POSITIVE LOGITS

 former

1.03

 Former

0.90

Former

0.90

ex

0.83

former

0.79

 ehemaligen

0.76

 ehemalige

0.73

 ancien

0.71

 ehemal

0.70

 formerly

0.69

Activations Density 0.104%

references to individuals who have held previous positions of power or office

No Comments

No Known Activations