INDEX

Explanations

nouns and keywords related to legal, medical, and artistic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 regioni

-0.48

onos

-0.46

Condol

-0.45

 agrí

-0.43

 réseau

-0.42

 conva

-0.42

 pericolo

-0.42

 gevaar

-0.42

❮

-0.42

POSITIVE LOGITS

">//

0.93

verwijspagina

0.80

 protoimpl

0.75

tagext

0.74

__':

0.73

ValueStyle

0.71

__":

0.70

 mega

0.62

RefNanny

0.62

 препратки

0.61

Activations Density 2.715%

nouns and keywords related to legal, medical, and artistic contexts

No Comments

No Known Activations