INDEX

Explanations

numerical values associated with measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 autorytatywna

-0.68

 estimés

-0.63

 ویکی‌پدی

-0.62

 EconPapers

-0.62

HasAnnotation

-0.59

 relâche

-0.56

TestBed

-0.56

 arşivlendi

-0.53

__":

-0.52

 otomatig

-0.52

POSITIVE LOGITS

 intStringLen

0.51

eien

0.47

zyż

0.46

Obrázky

0.45

öte

0.45

rillation

0.45

VideoCapture

0.45

OCCURRED

0.45

 Disadvantages

0.44



0.43

Activations Density 0.566%

numerical values associated with measurements or statistics

No Comments

No Known Activations