INDEX

Explanations

references to specific geopolitical regions and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Anſ

-0.83

ſelves

-0.79

 photolibrary

-0.74

 Jefus

-0.73

 purpoſe

-0.70

ſelf

-0.70

 doubtnut

-0.69

 Reſ

-0.67

 Majefty

-0.66

\\

-0.65

POSITIVE LOGITS

 مشين

0.66

 يتيمه

0.66

 للمعارف

0.59

#+#

0.55

 cilind

0.52

يميديا

0.51

onViewCreated

0.49

 Egipto

0.48

IContainer

0.48

 INVENTION

0.48

Activations Density 0.158%

references to specific geopolitical regions and entities

No Comments

No Known Activations