INDEX

Explanations

references to patents and patent documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Packer

-0.60

 decon

-0.51

مصادر

-0.48

 MonoBehaviour

-0.48

 Airlines

-0.47

SPJ

-0.47

 Meck

-0.45

InSection

-0.45

school

-0.44

Statics

-0.44

POSITIVE LOGITS

 patent

1.65

 Patent

1.53

 patents

1.48

patent

1.45

Patent

1.42

 Patents

1.34

 PATENT

1.25

 patente

1.18

 patented

1.14

 inventor

1.12

Activations Density 0.863%

references to patents and patent documents

No Comments

No Known Activations