INDEX

Explanations

legal terminology and references related to plaintiffs and defendants in a court context

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

parties in legal cases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

講

-0.35

Tal

-0.35

讲

-0.34

 plausible

-0.33

 plasticity

-0.33

 integration

-0.32

 POSSIBLE

-0.32

 equi

-0.32

 fous

-0.32

 orientation

-0.31

POSITIVE LOGITS

 Wiktionnaire

0.57

Manbalar

0.56

Datuak

0.52

queryInterface

0.52

protoimpl

0.51

 saites

0.51

 endregion

0.51

 referenties

0.49

IntoConstraints

0.48

endregion

0.48

Activations Density 0.125%

legal terminology and references related to plaintiffs and defendants in a court context

parties in legal cases

No Comments

No Known Activations