INDEX

Explanations

quantitative data related to accommodation capacity in various settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 millions

-0.85

two

-0.80

 Millions

-0.75

 billions

-0.74

Two

-0.71

two

-0.71

Two

-0.70

millions

-0.69

 jutaan

-0.69

TWO

-0.67

POSITIVE LOGITS

 dozen

1.35

 thirty

1.31

 twenty

1.30

 forty

1.27

 fifty

1.22

 sixty

1.21

Twenty

1.20

Thirty

1.19

 Thirty

1.17

Forty

1.15

Activations Density 0.441%

quantitative data related to accommodation capacity in various settings

No Comments

No Known Activations