INDEX

Explanations

legal and business language, using words and phrases common in contracts, court opinions, and corporate filings

oai_token-act-pair · gemini-2.0-flash

legal terminology and concepts

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

in

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Normdatei

-0.76

SharedDtor

-0.73

VIAF

-0.72

awaiter

-0.69

 المعيارى

-0.65

 дописавши

-0.65

tagHelperRunner

-0.62

makeConstraints

-0.61

 '\\;'

-0.61

RTLR

-0.61

POSITIVE LOGITS

 respect

0.59

so

0.57

 connection

0.56

no

0.54

 regard

0.49

chromedriver

0.49

rollo

0.49

chetto

0.48

 empe

0.47

Scalars

0.46

Activations Density 3.933%

legal and business language, using words and phrases common in contracts, court opinions, and corporate filings

legal terminology and concepts

in

No Comments

No Known Activations