INDEX

Explanations

terms related to efficiency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 intptr

-0.57



-0.53

tokenize

-0.53

 sikkert

-0.51

/**

-0.50

広い

-0.48

meldet

-0.48

 brancas

-0.47

rapid

-0.47

 Rivers

-0.47

POSITIVE LOGITS

 efficiency

2.10

 effectiveness

2.01

 Efficiency

1.97

Efficiency

1.89

 Effectiveness

1.87

efficiency

1.80

 EFFICIENCY

1.69

effectiveness

1.66

Effectiveness

1.65

 efficiencies

1.54

Activations Density 0.115%

terms related to efficiency in various contexts

No Comments

No Known Activations