INDEX

Explanations

comparative phrases and distinctions between approaches 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

Not in Any Lists

No Comments

Negative Logits

:✨

-0.57

AsUp

-0.57

 CreateTagHelper

-0.55

 дописавши

-0.48

 poud

-0.47

AndEndTag

-0.47

gonic

-0.46

 zoll

-0.42

 censiti

-0.41

 CanadaChoose

-0.41

POSITIVE LOGITS

 whether

0.81

Whether

0.66

whether

0.65

 Whether

0.63

 WHETHER

0.61

 differences

0.50

是否

0.50

かどうか

0.46

 是否

0.46

の違い

0.45

Activations Density 1.186%

comparative phrases and distinctions between approaches or concepts

No Comments

No Known Activations