INDEX

Explanations

vocabulary related to legal or medical assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

nitzer

-0.58

 tiên

-0.54

zension

-0.51

schemas

-0.49

""".

-0.49

ichan

-0.48

şiv

-0.48

]=='

-0.47

oderma

-0.47

phyla

-0.47

POSITIVE LOGITS

 autorytatywna

0.82

 تانيه

0.63

Personendaten

0.59

RefNanny

0.58

 مرئيه

0.56

expandindo

0.54

 Voyez

0.54

 fullt

0.53

 comigo

0.53

andaag

0.52

Activations Density 1.053%

vocabulary related to legal or medical assessments

No Comments

No Known Activations