INDEX

Explanations

words and phrases that are positive and helpful with a valence score of 5

oai_token-act-pair · gemini-2.0-flash

negative context

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 lccn

-0.53

addPreferredGap

-0.53

awtextra

-0.51

 alco

-0.48

velocityY

-0.47

)}</

-0.47

 besti

-0.45

 المعيارى

-0.44

ocally

-0.43

+'</

-0.43

POSITIVE LOGITS

TagMode

0.60

Zunanje

0.57

 مرئيه

0.57

couvrez

0.57

featureID

0.56

prefixer

0.55

AccessorTable

0.54

Datuak

0.53

XmlAccessType

0.52

CLUYE

0.52

Activations Density 5.220%

words and phrases that are positive and helpful with a valence score of 5

negative context

No Comments

No Known Activations