INDEX

Explanations

elements related to personal observations and actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.53

етесь

-0.52

신

-0.52

Suara

-0.50

+#+#

-0.50

gnition

-0.49

aughey

-0.47

DIRS

-0.47

lipop

-0.46

 المعيارى

-0.46

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.78

 للمعارف

0.78

 الحره

0.67

tagext

0.65

CreateModel

0.62

 WebDriverWait

0.59

 unfold

0.58

 ویکی‌پدیا

0.57

 Audiodateien

0.57

//-->

0.55

Activations Density 0.310%

elements related to personal observations and actions

No Comments

No Known Activations