INDEX

Explanations

terms related to optimization and improving efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.61

 Fälle

-0.57

ber

-0.56

bed

-0.54

wyd

-0.53

 great

-0.52

big

-0.52

Ger

-0.51

putc

-0.51

 آور

-0.51

POSITIVE LOGITS

optim

1.49

 Optim

1.47

 OPTIM

1.46

 optimisation

1.46

 optim

1.44

OPTIM

1.42

 Optimum

1.42

 opti

1.42

 optimise

1.40

 Optimus

1.37

Activations Density 0.110%

terms related to optimization and improving efficiency

No Comments

No Known Activations