INDEX

Explanations

phrases highlighting positive accomplishments and contributions

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

 때문

-0.52

neither

-0.51

 quelconque

-0.49

 siquiera

-0.48

<bos>

-0.47

다고

-0.45

вики

-0.44

UpDown

-0.44

ilidad

-0.43

 ممکن

-0.43

POSITIVE LOGITS

 wonderful

2.07

 fantastic

2.06

 terrific

1.92

 excellent

1.87

 amazing

1.80

wonderful

1.79

fantastic

1.77

 fabulous

1.76

 marvelous

1.75

 great

1.73

Activations Density 0.376%

phrases highlighting positive accomplishments and contributions

No Comments

No Known Activations