INDEX

Explanations

references to writers and their creative processes or works

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

the action of writing

np_acts-logits-general · gemini-2.0-flash

writing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

awtextra

-0.54

djangoproject

-0.52

entyfik

-0.51

iedene

-0.49

ệc

-0.49

 defStyleAttr

-0.45

 estimés

-0.45

LookAndFeel

-0.43

feira

-0.43

ChromeDriver

-0.43

POSITIVE LOGITS

 writing

3.47

 write

3.25

 Writing

3.00

writing

2.99

write

2.93

Writing

2.89

 written

2.87

 Write

2.85

 wrote

2.83

 writes

2.75

Activations Density 0.731%

references to writers and their creative processes or works

the action of writing

writing

No Comments

No Known Activations