INDEX

Explanations

references to legal terminology or concepts related to actions and classifications of wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

دانشنامهٔ

-0.86

IUrlHelper

-0.86

setupUi

-0.84

adaptiveStyles

-0.83

setVerticalGroup

-0.82

MigrationBuilder

-0.81

rawDesc

-0.81

########.

-0.81

 متعلقه

-0.79

 ExecuteAsync

-0.79

POSITIVE LOGITS

 life

0.46

“

0.45

El

0.45

or

0.42

 challenges

0.42

年から

0.41

ש

0.41

0.40

和他

0.40

 Кро

0.39

Activations Density 0.403%

references to legal terminology or concepts related to actions and classifications of wrongdoing

No Comments

No Known Activations