INDEX

Explanations

words and phrases that appear in legal opinions.

oai_token-act-pair · gemini-2.0-flash

technical and legal terms

np_token-act-pair-logits · gpt-4o-mini

legal text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 decoradas

-0.56

 كومونز

-0.54

 <=",

-0.54

 noires

-0.51

WriteLiteral

-0.51

 affari

-0.50

 religieuses

-0.50

 pertanto

-0.49

 auguri

-0.46

 sguardo

-0.46

POSITIVE LOGITS

 Вікі

0.70

ConstraintMaker

0.68

 requestCode

0.63

 оригіналу

0.63

+#+#

0.59

Искәрмәләр

0.56

ViewFeatures

0.55

Hochspringen

0.54

beforeEach

0.51

HttpEntity

0.51

Activations Density 5.087%

words and phrases that appear in legal opinions.

technical and legal terms

legal text

No Comments

No Known Activations