INDEX

Explanations

specific geographical locations or place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

/***/

-0.51

...

-0.46

 CreateTagHelper

-0.46

 talks

-0.44

aronne

-0.44

big

-0.44

Хро

-0.44

榎

-0.43

---

-0.43

rus

-0.42

POSITIVE LOGITS

出版年

0.83

-------------</

0.78

 فريبيس

0.73

хьтан

0.71

 démocr

0.69

mybatisplus

0.68

ьаж

0.66

 للاسماء

0.66

FontOfSize

0.66

ervlak

0.64

Activations Density 1.586%

specific geographical locations or place names

No Comments

No Known Activations