INDEX

Explanations

legal terms and names associated with cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 seriously

-0.45

zeichen

-0.44

таратура

-0.44

 regularly

-0.43

ηγ

-0.43

 semana

-0.42

too

-0.42

iseks

-0.42

SIGN

-0.42

AddRange

-0.41

POSITIVE LOGITS

ValueStyle

0.94

MigrationBuilder

0.78

NER

0.75

 surla

0.73

ChildScrollView

0.72

LookAnd

0.71

ner

0.70

ApiModelProperty

0.68

HasAnnotation

0.66

 []).

0.65

Activations Density 1.937%

legal terms and names associated with cases

No Comments

No Known Activations