INDEX

Explanations

phrases indicating permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Демографія

-0.88

ValueStyle

-0.87

 AssemblyCompany

-0.87

AndEndTag

-0.86

 StatelessWidget

-0.83

 AssemblyVersion

-0.82

numerusform

-0.81

 بيها

-0.79

 Ceinture

-0.78

SessionFactory

-0.77

POSITIVE LOGITS

 ALLOW

1.46

ALLOW

1.45

 Allow

1.35

 allow

1.32

 allows

1.27

 allowed

1.27

 Allows

1.27

Allows

1.21

Allow

1.20

 allowing

1.20

Activations Density 0.118%

phrases indicating permission or allowance

No Comments

No Known Activations