INDEX

Explanations

legal terms related to the imposition of penalties or judgments

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

Made

-0.79

 CreateTagHelper

-0.73

 Bayard

-0.67

-0.63

 soldati

-0.62

 Wiktionnaire

-0.60

 Manufactured

-0.59

providedIn

-0.58

 Butterworth

-0.58

IVEREF

-0.58

POSITIVE LOGITS

principalTable

0.72

 nonatomic

0.62

 Bool

0.58

 nube

0.57

protoimpl

0.56

vasive

0.54

 nơi

0.51

Opens

0.50

fsen

0.49

ompi

0.49

Activations Density 0.137%

legal terms related to the imposition of penalties or judgments

No Comments

No Known Activations