INDEX

Explanations

references to Twitter and its associated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

WebVitals

-0.81

Eſ

-0.78

 Monfieur

-0.76

 myſelf

-0.75

 Diſ

-0.74

 Inſ

-0.72

 ſeveral

-0.71

 Perſ

-0.71

 themſelves

-0.71

 ſever

-0.70

POSITIVE LOGITS

 الاطلاع

0.77

 Meksiku

0.74

 صوتيه

0.73

 Tapatalk

0.69

wikimedia

0.69

VersionUID

0.67

</s>

0.65

достатки

0.64

onomía

0.63

hamcrest

0.63

Activations Density 0.013%

references to Twitter and its associated content

No Comments

No Known Activations