INDEX

Explanations

legal terms and references related to petitions and court proceedings

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

ending in "er"

np_acts-logits-general · gemini-2.0-flash

legal roles and roles based on actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

IntoConstraints

-0.50

 consultato

-0.48

 للاسماء

-0.45

DockStyle

-0.44

 Cops

-0.43

 Heir

-0.43

༘

-0.42

 Minerva

-0.41

 Rooster

-0.41

parel

-0.40

POSITIVE LOGITS

 fellow

0.55

########.

0.53

ผู้

0.52

 medarbe

0.51

 người

0.49

 tää

0.48

 perſon

0.48

người

0.47

 esternos

0.45

ætter

0.44

Activations Density 0.762%

legal terms and references related to petitions and court proceedings

ending in "er"

legal roles and roles based on actions

No Comments

No Known Activations