INDEX

Explanations

proper nouns, particularly names and places

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

References, citations, or bibliography entries

np_acts-logits-general · gemini-2.0-flash

National and network

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 useDispatch

-0.59

bcryptjs

-0.58

 الحره

-0.58

 kiệm

-0.56

deleteAll

-0.55

$.}

-0.54

Tikang

-0.52

 auszu

-0.52

ziali

-0.51

"]];

-0.51

POSITIVE LOGITS

 National

0.70

 lccn

0.66

nationality

0.66

 Network

0.65

National

0.65

 network

0.65

0.64

 nitrogen

0.63

 Nath

0.63

Network

0.62

Activations Density 0.486%

proper nouns, particularly names and places

References, citations, or bibliography entries

National and network

No Comments

No Known Activations