INDEX

Explanations

references to specific languages, formats, and sizes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

NOPQRST

-0.68

 LIRE

-0.66

出版年

-0.65



-0.63

 WebDriverWait

-0.62

ArgumentParser

-0.61

VIAF

-0.61

++)

-0.60

 useNavigate

-0.60

laszt

-0.60

POSITIVE LOGITS

 format

0.62

 formato

0.53

íslu

0.49

pur

0.49

GroupLayout

0.47

الحياه

0.46

format

0.44

 вигля

0.43

tableFuture

0.43

 capacity

0.43

Activations Density 0.277%

references to specific languages, formats, and sizes in various contexts

No Comments

No Known Activations