INDEX

Explanations

references to upcoming events or episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ukone

-0.85

zmir

-0.82

 commercio

-0.78

Marcin

-0.74

 vooraf

-0.74

 hashMap

-0.74

hidup

-0.73

HasAnnotation

-0.73

rawdę

-0.73

\}\\

-0.72

POSITIVE LOGITS

nextProps

1.55

 next

1.55

 NEXT

1.50

next

1.41

 Next

1.35

NEXT

1.30

hasNext

1.27

Next

1.26

setNext

1.24

nextDouble

1.10

Activations Density 0.064%

references to upcoming events or episodes

No Comments

No Known Activations