INDEX

Explanations

legal arguments, including verbs like argue, contend, assert, and rely, and words related to legal documents such as constitutional and statute.

oai_token-act-pair · gemini-2.0-flash

arguments and assertions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.78

 CreateTagHelper

-0.77

 kasarigan

-0.65

 Roskov

-0.63

참고

-0.56

GEBURTS

-0.55

 المعيارى

-0.54

verwijspagina

-0.53

 sond

-0.52

 فريبيس

-0.52

POSITIVE LOGITS

 prochaines

0.53

 solidarité

0.52

 argumento

0.51

 disant

0.51

 investissements

0.50

 argumentos

0.49

tagext

0.49

abstractmethod

0.48

 مب

0.48

 lateinit

0.48

Activations Density 2.535%

legal arguments, including verbs like argue, contend, assert, and rely, and words related to legal documents such as constitutional and statute.

arguments and assertions

No Comments

No Known Activations