INDEX

Explanations

names associated with legal cases and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 isolado

-0.83

 Matilda

-0.82

 Obrador

-0.77

featureID

-0.76

 Josephine

-0.75

 وتسجيلات

-0.70

 merve

-0.69

GEBURTSDATUM

-0.69

 Mariam

-0.69

 Mendelssohn

-0.68

POSITIVE LOGITS

 Alan

0.86

Alan

0.81

 Steve

0.73

 ALAN

0.69

 Gary

0.68

Steve

0.68

 Keith

0.67

Gary

0.65

Dave

0.65

 Craig

0.63

Activations Density 0.624%

names associated with legal cases and documents

No Comments

No Known Activations