INDEX

Explanations

references to legal concepts and terminology related to liability and negligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

StructEnd

-0.60

EndGlobalSection

-0.52

pecabezas

-0.50

 parecer

-0.49

AnchorStyles

-0.47

 ویکی‌پدی

-0.45

MigrationBuilder

-0.45

 finnas

-0.45

 erreich

-0.45

 تانيه

-0.45

POSITIVE LOGITS

 qualify

0.90

 qualifies

0.89

 constitutes

0.88

 constitute

0.87

 enti

0.76

 automatically

0.70

 entitle

0.69

 constitu

0.67

 constituted

0.67

 counts

0.66

Activations Density 1.178%

references to legal concepts and terminology related to liability and negligence

No Comments

No Known Activations