INDEX

Explanations

terms related to quantities and measurements, particularly in the context of reduction or optimization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Ẫ

-0.58

ByExample

-0.56

 CGRect

-0.52

efeller

-0.49

CGRect

-0.48

metics

-0.48

setContentView

-0.48

 SafeMath

-0.48

 BoxFit

-0.47

rega

-0.47

POSITIVE LOGITS

 multiplicity

0.98

 multiple

0.98

multiple

0.90

 Multiple

0.90

 plurality

0.87

Multiple

0.85

 MULTIPLE

0.81

rrggbb

0.78

 múltiple

0.75

複数

0.75

Activations Density 0.690%

terms related to quantities and measurements, particularly in the context of reduction or optimization

No Comments

No Known Activations