INDEX

Explanations

phrases related to outcomes and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

providedIn

-0.73

Obrázky

-0.65

RSpec

-0.65

styleUrls

-0.64

 تضيفلها

-0.59

 ویکی‌پدیا

-0.59

randomUUID

-0.55

 CURIAM

-0.55

 utafitiHapana

-0.53

SBATCH

-0.52

POSITIVE LOGITS

 efforts

0.69

effort

0.66

 Paglinawan

0.66

 combining

0.63

 urma

0.62

 resourceCulture

0.61

 результате

0.61

efforts

0.60

 careful

0.59

 interplay

0.58

Activations Density 0.781%

phrases related to outcomes and results

No Comments

No Known Activations