INDEX

Explanations

opportunities in general

oai_token-act-pair · gemini-2.0-flash

exercise-related terms

np_token-act-pair-logits · gpt-4o-mini

exercise

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

例文帳に追加

-0.48

 supérieurs

-0.43

 quæ

-0.42

 eorum

-0.42

 publicitaires

-0.40

 négociations

-0.40

 صوتيه

-0.40

Hochspringen

-0.39

 carácter

-0.39

таратура

-0.38

POSITIVE LOGITS

 exercise

1.51

exercise

1.37

 Exercise

1.31

 exercising

1.30

Exercise

1.23

 exercised

1.22

exer

1.17

 demonstrating

1.16

 exercises

1.14

 display

1.13

Activations Density 1.350%

opportunities in general

exercise-related terms

exercise

No Comments

No Known Activations

opportunities in general

exercise-related terms

exercise

No Comments

No Known Activations