INDEX

Explanations

references to specific legal terms and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Distribuzione

-0.32

 Bioaccumulative

-0.32

 مُعرِّف

-0.32

ciatore

-0.31

ۜ

-0.30

 tardes

-0.30

┐

-0.29

抵抗

-0.29

 onOptions

-0.28

 CONDITION

-0.28

POSITIVE LOGITS

 propOrder

0.56

ExtendWith

0.54

iſten

0.54

 StatefulWidget

0.54

 hereafter

0.53

principalColumn

0.52

MessageOf

0.52

 hereinafter

0.52

 getItemCount

0.50

__);

0.49

Activations Density 0.700%

references to specific legal terms and entities

No Comments

No Known Activations