INDEX

Explanations

references to housing and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Philosophical

-0.69

 philo

-0.67

 PHILOS

-0.63

ritsar

-0.60

 stoned

-0.59

Mauricio

-0.58

gr

-0.58

 Strecken

-0.58

opar

-0.57

잎

-0.57

POSITIVE LOGITS

 housing

2.67

 Housing

2.38

housing

2.34

Housing

2.28

 HOUSING

2.20

 hous

1.25

 logement

1.24

 housed

1.22

 vivienda

1.19

 perumahan

1.12

Activations Density 0.096%

references to housing and related terms

No Comments

No Known Activations