INDEX

Explanations

terms related to trust and consent in personal and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

WithIOException

-0.63

aarrggbb

-0.62

tvguidetime

-0.62

makeText

-0.60

httphttps

-0.56

 GoogleFonts

-0.54

Datuak

-0.53

 vinaigre

-0.53

Демографія

-0.52

verwijspagina

-0.50

POSITIVE LOGITS

 entrust

0.66

 surrender

0.66

 trusting

0.65

 willingly

0.64

 Surrender

0.59

 cede

0.59

 Vertrauen

0.56

 fiducia

0.55

 accepté

0.54

клопе

0.54

Activations Density 0.313%

terms related to trust and consent in personal and legal contexts

No Comments

No Known Activations