INDEX

Explanations

references to the concept of "zero" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

:],

-0.72

ukone

-0.72

}*/

-0.67

 '../

-0.66

 kautta

-0.64

://"

-0.63

 rosca

-0.63

 obligé

-0.63

})*/

-0.63

Vidite

-0.63

POSITIVE LOGITS

zero

1.19

 Zero

1.16

 zero

1.14

 ZERO

1.13

Zero

1.13

zeros

1.10

ZERO

1.07

 zeros

1.05

Zer

1.03

Zeros

1.02

Activations Density 0.087%

references to the concept of "zero" in various contexts

No Comments

No Known Activations