INDEX

Explanations

references to time, particularly specific years and seasons

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

Negative Logits

neurial

-0.62

yii

-0.59

estres

-0.57

ürtel

-0.56

Rez

-0.56

 Peach

-0.56

stell

-0.56

 Kepler

-0.55

madeus

-0.55

✨:

-0.55

POSITIVE LOGITS

ORROW

0.73

 Paglinawan

0.72

 kasarigan

0.61

#+#

0.60

terday

0.57

DidLoad

0.56

Notae

0.56

 yesterday

0.56

InvalidProtocol

0.56

TouchEvent

0.56

Activations Density 0.047%

references to time, particularly specific years and seasons

No Known Activations