INDEX

Explanations

references to the concept of "cause"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

tispiece

-0.70

<?=

-0.69

<?

-0.65

 useStyles

-0.64

ViewBag

-0.63

енча

-0.59

}*/

-0.59

"><?=

-0.59

BeginContext

-0.58

().__

-0.56

POSITIVE LOGITS

 cause

1.73

cause

1.65

 Cause

1.65

Cause

1.56

 CAUSE

1.53

CAUSE

1.44

cuz

1.29

 causes

1.23

cos

1.22

 causa

1.12

Activations Density 0.130%

references to the concept of "cause"

No Comments

No Known Activations