INDEX

Explanations

terms related to legal and regulatory frameworks, particularly those involving healthcare and environmental practices

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

 recommandons

-0.34

 pourriez

-0.31

 Mats

-0.30

ElementException

-0.29

 uncovered

-0.29

ry

-0.28

StylePriority

-0.28

 trouverez

-0.28

-0.27

POSITIVE LOGITS

 Congressional

0.94

 congressional

0.93

 federal

0.92

 Majefty

0.87

ederal

0.83

 FEDERAL

0.83

 Federal

0.83

federal

0.82

Federal

0.77

 federally

0.76

Activations Density 2.423%

terms related to legal and regulatory frameworks, particularly those involving healthcare and environmental practices

No Comments

No Known Activations