INDEX

Explanations

instances of specific legal terminology or identifiers in legal documents

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

AddHtmlAttribute

-0.72

-0.64

)}_

-0.61

 Waray

-0.56

Hochspringen

-0.54

istisches

-0.53

}}_{

-0.53

XmlAccessorType

-0.52

 &___

-0.50

 Wikimedijinoj

-0.49

POSITIVE LOGITS

 themſelves

0.71

 purpoſe

0.69

 himſelf

0.69

 myſelf

0.66

 poffible

0.65

ſy

0.64

 uſe

0.63

 uſed

0.61

 ſtate

0.60

 houſe

0.60

Activations Density 0.434%

instances of specific legal terminology or identifiers in legal documents

No Comments

No Known Activations