INDEX

Explanations

references to legal concepts and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

StoryboardSegue

-0.87

toMatchSnapshot

-0.69

✨:

-0.69

pośred

-0.68

enderror

-0.65

 Améli

-0.64

omitempty

-0.62

 المعيارى

-0.61

ngdoc

-0.61

 cherchés

-0.59

POSITIVE LOGITS

law

4.55

Law

3.78

law

3.62

Law

3.60

LAW

3.49

LAW

3.25

 laws

3.14

 Laws

2.74

laws

2.54

Laws

2.50

Activations Density 0.080%

references to legal concepts and terminology

No Comments

No Known Activations