INDEX

Explanations

legal terminology related to court judgments and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kids

-0.48

 amazing

-0.48

-0.47

 wonderful

-0.46

-0.44

 lovely

-0.42

bo

-0.41

my

-0.41

you

-0.40

eds

-0.40

POSITIVE LOGITS

<bos>

0.99

setVerticalGroup

0.97

GEBURTSDATUM

0.97

stateProvider

0.91

 propOrder

0.91

 resourceCulture

0.89

+:+

0.87

WebElementEntity

0.86

Kjelder

0.85

 '\\;'

0.85

Activations Density 4.833%

legal terminology related to court judgments and findings

No Comments

No Known Activations