INDEX

Explanations

technical documents such as patents and scientific papers.

oai_token-act-pair · gemini-2.0-flash

phrases related to claims or legal terminology

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

intellectual property

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

 Мексичка

-0.63

moveToFirst

-0.63

exels

-0.56

 AssemblyProduct

-0.56

 Roskov

-0.55

Cyfeiriadau

-0.52

存于互联网档案馆

-0.52

ichio

-0.50

#![

-0.50

 Administrativna

-0.50

POSITIVE LOGITS

 Claims

0.59

 claims

0.58

claims

0.56

 claimed

0.53

 skilled

0.50

pected

0.50

 thro

0.49

entuh

0.49

سانی

0.49

 Someone

0.49

Activations Density 3.583%

technical documents such as patents and scientific papers.

phrases related to claims or legal terminology

intellectual property

No Comments

No Known Activations