INDEX

Explanations

terms related to patents and intellectual property

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

Niels

-0.74

zbo

-0.73

Kig

-0.73

 Valk

-0.72

 Maja

-0.71

preuve

-0.71

Aks

-0.70

 gills

-0.70

 Dodd

-0.69

EPL

-0.68

POSITIVE LOGITS

pat

1.07

Pat

1.03

pat

1.00

 Patria

0.97

Pat

0.97

 Patro

0.93

 Pats

0.92

Patches

0.90

 Patel

0.88

?>">

0.87

Activations Density 0.806%

terms related to patents and intellectual property

No Comments

No Known Activations