INDEX

Explanations

quantifiable evaluations of groups or categories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Preceding superlative adjectives

np_acts-logits-general · gemini-2.0-flash

most, largest, highest, newest, best

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

est

-0.61

MORE

-0.53

Best

-0.52

bootstrapcdn

-0.49

nya

-0.48

 besonders

-0.48

er

-0.47

 hosszú

-0.47

特别

-0.46

 lieber

-0.46

POSITIVE LOGITS

=$?

1.13

rungsseite

0.94

 ujednoznacz

0.94

 surla

0.94

 StatefulWidget

0.94

ContentAsync

0.88

"])

0.86

]){

0.84

 StatelessWidget

0.83

 leggi

0.81

Activations Density 0.192%

quantifiable evaluations of groups or categories

Preceding superlative adjectives

most, largest, highest, newest, best

No Comments

No Known Activations