INDEX

Explanations

terms related to weight and its management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 nahilalakip

-0.78

 Wikispecies

-0.74

FontOfSize

-0.72

sslich

-0.68

harusnya

-0.65

mejores

-0.62

✨:

-0.62

цездатний

-0.61

:✨

-0.61

 Diener

-0.60

POSITIVE LOGITS

 weights

1.36

weight

1.35

 Weight

1.30

 weight

1.30

WEIGHT

1.27

weights

1.26

 WEIGHT

1.25

Weight

1.19

 Weights

1.15

Weights

1.06

Activations Density 0.137%

terms related to weight and its management

No Comments

No Known Activations