INDEX

Explanations

terms related to patents and patenting processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Evers

-0.85

agoza

-0.84

Zeneca

-0.81

 Riva

-0.77

 Briggs

-0.77

Thing

-0.74

 Turks

-0.73

 Creole

-0.73

 znaczy

-0.73

Yag

-0.73

POSITIVE LOGITS

Pat

1.41

PAT

1.40

pat

1.31

Pat

1.28

pat

1.27

 Pats

1.25

PAT

1.25

 Patro

1.17

 pats

1.09

 Paterson

1.06

Activations Density 0.203%

terms related to patents and patenting processes

No Comments

No Known Activations