INDEX

Explanations

specific properties and categories in structured data

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

RGB color values

np_acts-logits-general · gemini-2.0-flash

colors, sex, or media

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

-0.79

 receptor

-0.78

-0.77

 rato

-0.77

 Raya

-0.75

 rage

-0.75

 Receptor

-0.74

 Randall

-0.73

 rada

-0.73

 Richards

-0.73

POSITIVE LOGITS

 indisponible

0.40

 مشين

0.39

ContentAsync

0.38

IsContent

0.38

enterOuterAlt

0.36

lgari

0.36

łasz

0.36

makeText

0.35

 TableColumn

0.35

============

0.34

Activations Density 0.851%

specific properties and categories in structured data

RGB color values

colors, sex, or media

No Comments

No Known Activations