INDEX

Explanations

words and phrases related to printing and printers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 subgoals

-0.84

Referanser

-0.83

 înd

-0.80

 auroit

-0.80

 eût

-0.79

arakhand

-0.78

 pouvoit

-0.78

 devenus

-0.77

Caw

-0.77

Revenir

-0.76

POSITIVE LOGITS

 prints

1.38

 Print

1.38

PRINT

1.36

 PRINT

1.36

 print

1.33

Print

1.26

 printing

1.24

 Prints

1.20

print

1.19

 printed

1.19

Activations Density 0.059%

words and phrases related to printing and printers

No Comments

No Known Activations