INDEX

Explanations

details about specific rooms and their features in a property

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

expandindo

-0.75

Jeografia

-0.74

 CreateTagHelper

-0.72

 Exactos

-0.72

 Audiodateien

-0.66

MemoryWarning

-0.66

enumi

-0.65

 &___

-0.63

 виправивши

-0.63

 protoimpl

-0.61

POSITIVE LOGITS

 Airbnb

0.70

 rental

0.64

 guests

0.64

 rentals

0.57

Airbnb

0.54

 renters

0.52

 booking

0.51

 rented

0.51

 surla

0.51

 occupancy

0.51

Activations Density 0.031%

details about specific rooms and their features in a property

No Comments

No Known Activations