INDEX

Explanations

references to laws and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Monfieur

-1.00

BibitemShut

-0.90

 purpoſe

-0.88

 Theſe

-0.85

pośred

-0.84

 Jefus

-0.83

 eenige

-0.82

 pleaſure

-0.81

 themſelves

-0.81

 Chriftian

-0.81

POSITIVE LOGITS

law

3.44

Law

3.19

Law

2.97

LAW

2.96

law

2.86

LAW

2.56

 laws

2.49

 Laws

2.17

laws

1.93

 LAWS

1.93

Activations Density 0.062%

references to laws and legal terminology

No Comments

No Known Activations