INDEX

Explanations

concepts related to optimization and efficiency

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

Tokens after specific words such as "maximize" or "variant"

np_acts-logits-general · gemini-2.0-flash

improve or optimize

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 informée

-0.64

writeField

-0.57

bootstrapcdn

-0.52

fromnode

-0.50

domada

-0.50

 للمعارف

-0.49

NOWLEDG

-0.48

pédie

-0.48

 espectaculares

-0.48

 LoggerFactory

-0.47

POSITIVE LOGITS

 improvements

0.66

 Improvements

0.63

Improvements

0.62

 improvement

0.56

improve

0.53

improvement

0.52

Improvement

0.52

 améli

0.52

 Improvement

0.52

 improved

0.51

Activations Density 0.000%

concepts related to optimization and efficiency

Tokens after specific words such as "maximize" or "variant"

improve or optimize

No Comments

No Known Activations