INDEX

Explanations

phrases that talk about learning lessons

oai_token-act-pair · gemini-2.0-flash

lesson

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/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.4.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

verk

-0.54

 spol

-0.47

 purchaser

-0.44

 passport

-0.43

invalid

-0.43

 Passport

-0.43

 Dwell

-0.42

länder

-0.42

 versch

-0.41

 verk

-0.40

POSITIVE LOGITS

 lesson

0.94

 lessons

0.92

 leçon

0.84

<bos>

0.84

lessons

0.84

Lessons

0.80

出版年

0.80

LookAnd

0.79

 Lessons

0.78

 leçons

0.78

Activations Density 0.723%

phrases that talk about learning lessons

lesson

No Comments

No Known Activations