INDEX

Explanations

terms related to complementary relationships or enhancements between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

czyn

-0.33

 ابت

-0.33

ItemLayout

-0.32

RegressionTest

-0.31

万人

-0.30

 Waterproof

-0.30

}]{

-0.29

delwed

-0.29

ufact

-0.29

ürger

-0.29

POSITIVE LOGITS

 complement

1.20

 complements

1.13

 Complement

1.12

Complement

1.09

 complementary

1.09

complement

1.05

 complementa

1.05

 compliment

1.04

 Complementary

1.00

 complemented

0.97

Activations Density 0.540%

terms related to complementary relationships or enhancements between concepts

No Comments

No Known Activations