INDEX

Explanations

phrases indicating the source of information

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.81

cokinetics

-0.75

 OnTrigger

-0.70

IGraphics

-0.66

깐

-0.66

 saites

-0.66

timeScale

-0.65

 jsPsych

-0.63

MigrationBuilder

-0.62

rolex

-0.62

POSITIVE LOGITS

 FROM

1.34

FROM

1.30

 From

1.21

from

1.17

From

1.16

 from

1.14

 từ

1.05

 desde

1.03

desde

1.01

 Từ

0.99

Activations Density 0.158%

phrases indicating the source of information

No Comments

No Known Activations