INDEX

Explanations

terms related to approximation and estimates

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

 songs

-0.57

sen

-0.55

-0.54

希

-0.53

 ngừa

-0.53

 fullt

-0.50

ola

-0.50

den

-0.49

rmtree

-0.49

stry

-0.49

POSITIVE LOGITS

 approxim

1.36

 approximate

1.31

 Approximate

1.28

 approximated

1.27

approximate

1.22

 approx

1.22

 Approx

1.21

Approx

1.18

 Approximation

1.18

 approximation

1.18

Activations Density 0.211%

terms related to approximation and estimates

No Comments

No Known Activations