INDEX

Explanations

legal terminology related to liability and permissions in software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Roskov

-1.36

oredCriteria

-1.36

 nahilalakip

-1.23

NameInMap

-1.14

RTEE

-1.06

addCriterion

-1.02

contentLoaded

-1.00

 Савезне

-0.99

 kasarigan

-0.99

WriteBarrier

-0.97

POSITIVE LOGITS

 ioutil

0.53

 furt

0.43

 spis

0.43

Again

0.39

 Again

0.38

 tomen

0.38

ُ

0.38

かっ

0.38

сп

0.38

 remercie

0.38

Activations Density 0.242%

legal terminology related to liability and permissions in software

No Comments

No Known Activations