INDEX

Explanations

terms related to legal concepts and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ummings

-0.57

phorus

-0.50

diyesi

-0.50

RIEL

-0.49

ources

-0.49

 Bande

-0.48

Mirage

-0.48

primary

-0.47

mberto

-0.47

 obserw

-0.46

POSITIVE LOGITS

law

0.91

LAW

0.88

Law

0.78

Law

0.74

 Legal

0.71

 LEGAL

0.69

 legal

0.69

law

0.69

LAW

0.68

 lawyer

0.66

Activations Density 0.264%

terms related to legal concepts and frameworks

No Comments

No Known Activations

terms related to legal concepts and frameworks

No Comments

No Known Activations