INDEX

Explanations

the beginning of a new section or topic in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.44

lotz

-0.43

Lef

-0.41

."

-0.40

be

-0.40

 Großen

-0.39

κέ

-0.39

ca

-0.39

 PartialEq

-0.38

ござ

-0.38

POSITIVE LOGITS

Personendaten

1.08

GoogleApiClient

0.93

 Paglinawan

0.92

 Baillargeon

0.90

niająca

0.90

 autorytatywna

0.89

tvguidetime

0.89

IsContent

0.88

 Biôgrafia

0.87

Enllaces

0.86

Activations Density 0.217%

the beginning of a new section or topic in text

No Comments

No Known Activations