INDEX

Explanations

terms and phrases related to permissions, allowances, and legal or procedural regulations

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

permission or allowance

np_acts-logits-general · gemini-2.0-flash

allowed, permitted, permissible

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

 escaleras

-0.42

 dificuldades

-0.38

 pensions

-0.37

ciera

-0.37

 MonoBehaviour

-0.36

だ

-0.36

GGLE

-0.35

 Maß

-0.35

 judgment

-0.35

kkue

-0.34

POSITIVE LOGITS

 Allowed

1.09

 allowed

1.06

allowed

1.02

Allowed

1.00

 permitted

0.94

 ALLOWED

0.89

 allowable

0.89

permitted

0.86

 permitido

0.80

 permissible

0.76

Activations Density 0.567%

terms and phrases related to permissions, allowances, and legal or procedural regulations

permission or allowance

allowed, permitted, permissible

No Comments

No Known Activations