INDEX

Explanations

terms related to patent applications and filings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

BeginContext

-0.64

 MainAxisSize

-0.55

 BoxFit

-0.54

解

-0.53

SequentialGroup

-0.53

 conscience

-0.52

ConstraintMaker

-0.51

bootstrapcdn

-0.51

porn

-0.50

 Patrimonio

-0.49

POSITIVE LOGITS

 Examiner

0.69

 examiner

0.66

 examiners

0.65

PCT

0.63

 filing

0.61

 patent

0.60

PTO

0.60

 prosecution

0.59

pat

0.59

examiner

0.58

Activations Density 0.741%

terms related to patent applications and filings

No Comments

No Known Activations