INDEX

Explanations

references to apartments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 '\\;'

-0.90

oredCriteria

-0.86

GetAxis

-0.78

Rüyada

-0.76

httphttps

-0.75

voyez

-0.74

bootstrapcdn

-0.72

исленность

-0.72

 Laus

-0.72

bewerken

-0.71

POSITIVE LOGITS

 apartment

1.52

 Apartment

1.40

 apartments

1.35

Apartment

1.31

apartment

1.21

 Apartments

1.18

 APART

1.08

 apartamento

1.02

公寓

0.97

Apartments

0.93

Activations Density 0.072%

references to apartments

No Comments

No Known Activations