INDEX

Explanations

terms related to privacy and private entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 onOptions

-0.79

GEBURTS

-0.71

็จ

-0.68

Sébastien

-0.68

 épis

-0.65

 thúc

-0.65

 cref

-0.65

=="

-0.65

 souha

-0.64

 HttpHeaders

-0.64

POSITIVE LOGITS

 private

1.28

 Private

1.25

Private

1.20

PRIVATE

1.17

 PRIVATE

1.12

 privada

1.05

private

1.05

 Privat

1.03

Pvt

1.02

 privately

1.01

Activations Density 0.043%

terms related to privacy and private entities

No Comments

No Known Activations