INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ApiModel

-0.63

Hauptartikel

-0.56

dom

-0.55

 ball

-0.55

imageURL

-0.55

expandindo

-0.54

&__

-0.54

braucher

-0.54

 دليل

-0.52

 مشين

-0.52

POSITIVE LOGITS

 thanking

1.61

 gratitude

1.58

 thankful

1.50

 grateful

1.50

 thanked

1.41

 thank

1.38

 Gratitude

1.35

thank

1.29

 remercier

1.22

 THANK

1.18

Activations Density 0.080%

expressions of gratitude and appreciation

No Comments

No Known Activations