INDEX

Explanations

keywords and references that denote structure and content within a written document

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

after periods or quotation marks

np_acts-logits-general · gemini-2.0-flash

crochet activities

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.71

########.

-0.52

 consultato

-0.52

oredCriteria

-0.50

IndentedString

-0.49

FunctionFlags

-0.48

MigrationBuilder

-0.47

sizeCache

-0.46

 invokingState

-0.44

Sklici

-0.44

POSITIVE LOGITS

SequentialGroup

0.54

帖最后由

0.39

additional

0.37

 additional

0.34

 добавил

0.34

RefreshLayout

0.33

 memoria

0.33

Zo

0.32

 dodatkowe

0.32

 added

0.32

Activations Density 0.616%

keywords and references that denote structure and content within a written document

after periods or quotation marks

crochet activities

No Comments

No Known Activations