INDEX

Explanations

terminology related to legal proceedings and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.72

Portale

-0.55

Datuak

-0.54

!*\

-0.51

PropertyChanging

-0.50

RenderAtEndOf

-0.50

GEBURTSDATUM

-0.49

 دیکھیے

-0.48

Diweddarwch

-0.48

 surla

-0.48

POSITIVE LOGITS

all

3.34

 semua

2.58

 todas

2.54

 tutte

2.51

 всех

2.44

 every

2.40

all

2.37

 everything

2.37

 toutes

2.28

ALL

2.27

Activations Density 3.119%

terminology related to legal proceedings and processes

No Comments

No Known Activations