INDEX

Explanations

mentions of pairs or groups of items or concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Various

-0.45

 various

-0.43

all

-0.42

各种

-0.39

Various

-0.38

 pelbagai

-0.38

 berbagai

-0.37

 variés

-0.37

various

-0.36

 tất

-0.36

POSITIVE LOGITS

two

0.78

two

0.77

 deux

0.77

兩種

0.76

兩個

0.73

Two

0.71

 ujednoznacz

0.71

 zwei

0.71

两个

0.71

 dvě

0.68

Activations Density 0.898%

mentions of pairs or groups of items or concepts

No Known Activations