INDEX

Explanations

terms related to efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

openqa

-0.78

 Marston

-0.77

FundMe

-0.77

RUB

-0.75

hasNext

-0.73

llten

-0.72

 Médico

-0.71

 Haver

-0.71

/**

-0.70

 ControllerBase

-0.70

POSITIVE LOGITS

 efficiency

1.49

fficiencies

1.42

 efficient

1.37

efficient

1.36

 Efficiency

1.36

 efficiencies

1.35

Efficiency

1.31

 EFFICIENCY

1.30

efficiency

1.28

fficient

1.21

Activations Density 0.111%

terms related to efficiency

No Comments

No Known Activations