INDEX

Explanations

words related to research, code, and food

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تانيه

-0.74

 Normdatei

-0.63

<bos>

-0.62

TagMode

-0.60

 Pingback

-0.57

-0.55

IndentedString

-0.55

 Réponses

-0.53

 ISNI

-0.52

AllAfrica

-0.52

POSITIVE LOGITS

謡

0.54

 jspb

0.52

 linkovi

0.51

Tembelea

0.50

️

0.49

])):

0.49

gelt

0.48

warts

0.48

 gears

0.48

paj

0.48

Activations Density 24.568%

words related to research, code, and food

No Comments

No Known Activations