INDEX

Explanations

passive voice constructions and actions indicating moving or changing status

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

past tense verbs followed by specific words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Compensation

-0.43

derivative

-0.42

Contributing

-0.35

 derivative

-0.35

esch

-0.35

avista

-0.34

 پی

-0.34

ایش

-0.34

lesias

-0.34

Merkmale

-0.34

POSITIVE LOGITS

MENAFN

0.51

InjectAttribute

0.50

DoubleQuotes

0.49

bootstrapcdn

0.48

Chham

0.46

haikusbot

0.45

UnknownFieldSet

0.44

 PeEnEo

0.43

 MenuView

0.41

лтемелер

0.41

Activations Density 0.088%

passive voice constructions and actions indicating moving or changing status

past tense verbs followed by specific words

No Comments

No Known Activations