INDEX

Explanations

phrases indicating permission or prohibition

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

DllImport

-0.50

 pacchetto

-0.48

 rifer

-0.48

cektir

-0.47

hav

-0.46

 sonno

-0.46

vœ

-0.46

LoggerFactory

-0.45

zeciw

-0.44

\}_{

-0.44

POSITIVE LOGITS

 allowed

2.95

 Allowed

2.71

allowed

2.57

 permitted

2.50

 ALLOWED

2.35

Allowed

2.23

permitted

1.94

 permissible

1.64

ALLOWED

1.63

 allowable

1.59

Activations Density 0.172%

phrases indicating permission or prohibition

No Comments

No Known Activations