INDEX

Explanations

terms related to legal and judicial contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

is

-1.73

are

-1.37

are

-1.03

là

-1.03

be

-1.01

 êtes

-0.98

 είναι

-0.95

 být

-0.95

 être

-0.94

 está

-0.94

POSITIVE LOGITS

 EconPapers

1.05

 CURIAM

0.84

ConstraintMaker

0.63

 does

0.63

 nonatomic

0.63

does

0.62

 ModelExpression

0.61

did

0.60

TargetException

0.60

setVerticalGroup

0.60

Activations Density 1.667%

terms related to legal and judicial contexts

No Comments

No Known Activations