INDEX

Explanations

references to specific locations, particularly residences and homes related to individuals involved in criminal activities

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

houses or living places

np_acts-logits-general · gemini-2.0-flash

people's homes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

❋

-0.61

esercito

-0.58

bonsoir

-0.56

">//

-0.56

eryn

-0.55

]})

-0.55

toppers

-0.54

 للاسماء

-0.53

 تانيه

-0.52

⁩

-0.51

POSITIVE LOGITS

 homes

1.61

 house

1.59

 residence

1.55

 home

1.52

 apartment

1.42

 residences

1.33

 houses

1.29

 dwelling

1.22

 rumah

1.22

 apartments

1.18

Activations Density 0.252%

references to specific locations, particularly residences and homes related to individuals involved in criminal activities

houses or living places

people's homes

No Comments

No Known Activations