INDEX

Explanations

legal terms and references related to documentation and dates

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Year following a month

np_acts-logits-general · gemini-2.0-flash

dates and subsequent events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

AndEndTag

-0.65

 autorytatywna

-0.63

 تضيفلها

-0.59

 queſta

-0.56

Aholisi

-0.56

 createSprite

-0.52

NameInMap

-0.52

⤹

-0.51

richTextPanel

-0.51

Tikang

-0.51

POSITIVE LOGITS

 subsequent

0.58

 later

0.54

 Later

0.50

 subsequently

0.47

Later

0.46

 ensuing

0.45

 Subsequent

0.43

帖最后由

0.43

 afterwards

0.39

 thereafter

0.38

Activations Density 0.604%

legal terms and references related to documentation and dates

Year following a month

dates and subsequent events

No Known Activations