INDEX

Explanations

relationships between two or more entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

กับ

-0.43

SSM

-0.42

cnia

-0.41

isPrime

-0.40

agama

-0.39

Third

-0.37

 retrait

-0.37

vs

-0.36

ouncer

-0.36

lå

-0.36

POSITIVE LOGITS

 together

1.64

 elkaar

1.51

 saling

1.46

 mutually

1.44

together

1.42

 juntos

1.39

 Together

1.39

 einander

1.36

Together

1.32

 TOGETHER

1.31

Activations Density 1.390%

relationships between two or more entities or concepts

No Comments

No Known Activations