INDEX

Explanations

mentions of specific locations or places

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

"place" or "places"

np_acts-logits-general · gemini-2.0-flash

place or places

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

retudo

-0.51

Conclusie

-0.49

 onStart

-0.49

 borboleta

-0.48

ignoire

-0.48

rinhos

-0.47

Autowired

-0.47

 biometric

-0.47

IMDG

-0.46

 Navarra

-0.46

POSITIVE LOGITS

place

1.12

 PLACE

1.05

PLACE

1.04

Place

1.01

 Place

1.00

 place

0.94

places

0.91

Places

0.88

 Places

0.82

 places

0.78

Activations Density 0.239%

mentions of specific locations or places

"place" or "places"

place or places

No Comments

No Known Activations