INDEX

Explanations

references to numerical data or statistics, particularly in relation to events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ویکی‌پدیا

-0.72

 Normdatei

-0.67

Билгалдахарш

-0.67

الدراسه

-0.52

 configureStore

-0.52

 reafon

-0.51

 sacré

-0.50

 kaarangay

-0.50

ัส

-0.50

expandindo

-0.49

POSITIVE LOGITS

pm

1.01

pm

0.90

am

0.84

PM

0.83

PM

0.80

AM

0.65

AM

0.63

am

0.63

 phút

0.59

Activations Density 0.091%

references to numerical data or statistics, particularly in relation to events or occurrences

No Comments

No Known Activations