INDEX

Explanations

the beginning of a document or significant new sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.50

-0.49

…

-0.45

$\

-0.44

-0.43

 further

-0.42

or

-0.41

…

-0.41

 under

-0.41

POSITIVE LOGITS

 ویکی‌پدیا

1.45

Geplaatst

1.33

帖最后由

1.21

 autorytatywna

1.18

makeConstraints

1.13

Portale

1.11

iastes

1.08

 kaarangay

1.07

KommentareTeilen

1.06

Personendaten

1.05

Activations Density 0.023%

the beginning of a document or significant new sections

No Comments

No Known Activations