INDEX

Explanations

legal code citations and references.

oai_token-act-pair · gemini-2.0-flash

legal documents

np_token-act-pair-logits · gemini-2.0-flash

legal/formal "shall"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Legături

-0.51

 ModelExpression

-0.48

المكان

-0.46

obos

-0.44

 usually

-0.44

 typically

-0.43

vs

-0.43

RegressionTest

-0.43

 generally

-0.42

Len

-0.42

POSITIVE LOGITS

EndInit

0.78

shall

0.78

 shall

0.75

 Shall

0.71

uksessa

0.67

 ſhall

0.62

MLLoader

0.59

 Cæsar

0.59

 shal

0.59

Shall

0.56

Activations Density 2.303%

legal code citations and references.

legal documents

legal/formal "shall"

No Comments

No Known Activations