INDEX

Explanations

identifiers related to database schemas and unique keys

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

unique items or keys

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

 متعلقه

-0.65

Hochspringen

-0.52

 estekak

-0.49

 MainAxisSize

-0.49

 كومونز

-0.49

Geplaatst

-0.46

 Infórmanos

-0.46

-------------</

-0.45

 TextInputType

-0.45

onActivityResult

-0.45

POSITIVE LOGITS

 unique

0.47

 UNIQUE

0.41

 aspect

0.40

 arşivlendi

0.39

 Unique

0.38

 useParams

0.38

Unique

0.37

 aspects

0.36

unique

0.35

 GenerationType

0.35

Activations Density 0.002%

identifiers related to database schemas and unique keys

unique items or keys

No Comments

No Known Activations