INDEX

Explanations

medical terms related to a specific disease and treatment

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 emphat

-0.96

 pymysql

-0.95

 Souha

-0.93

 Traité

-0.92

 bourg

-0.91

 Præ

-0.91

 accla

-0.89

 Mlle

-0.87

 smtplib

-0.86

Væ

-0.85

POSITIVE LOGITS

 facilities

0.80

 amenities

0.74

 సౌకర్య

0.67

 locations

0.67

 spaces

0.66

 facility

0.65

 amenity

0.65

 restrooms

0.65

Amenities

0.64

 Facilities

0.63

Activations Density 0.673%

medical terms related to a specific disease and treatment

No Comments

No Known Activations