INDEX

Explanations

phrases that indicate exceptions or limitations related to classifications or processes

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

 perfec

-0.51

roster

-0.49

+#+#

-0.49

InstanceState

-0.48

 geothermal

-0.47

DaoImpl

-0.45

viz

-0.45

IDAY

-0.45

eries

-0.44

WidgetItem

-0.44

POSITIVE LOGITS

 Приступљено

0.65

adpleegd

0.60

basicConfig

0.60

 صوتيه

0.60

 gynhyrchwyd

0.59

UnitTesting

0.58

EndProject

0.55

CloseOperation

0.55

 AssemblyCulture

0.54

клопе

0.54

Activations Density 0.654%

phrases that indicate exceptions or limitations related to classifications or processes

No Comments

No Known Activations