INDEX

Explanations

words that usually follow prepositions or conjunctions

oai_token-act-pair · gemini-2.0-flash

state of being

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

 CHAPITRE

-0.59

 quæ

-0.58

 fascic

-0.57

 autrefois

-0.57

 AspNetCore

-0.57

 myſelf

-0.54

+#+#

-0.53

 quitte

-0.50

 religieuses

-0.50

 CreateTagHelper

-0.49

POSITIVE LOGITS

bootstrapcdn

0.56

icef

0.49

ánto

0.48

+#+

0.48

ukses

0.47

ureka

0.47

 births

0.46

ergies

0.45

OGND

0.44

enumii

0.44

Activations Density 43.552%

words that usually follow prepositions or conjunctions

state of being

No Comments

No Known Activations