INDEX

Explanations

terms related to health and well-being, particularly focusing on the concept of 'healthy'

oai_token-act-pair · gpt-3.5-turbo

references to health and wellness, particularly focusing on the concept of being healthy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ariat

-0.78

 angrily

-0.74

raped

-0.71

 swoop

-0.67

akedown

-0.64

ingo

-0.63

acqu

-0.63

ighty

-0.61

Publisher

-0.61

 infamous

-0.61

POSITIVE LOGITS

 isot

1.01

tarian

0.81

 dose

0.80

 lifestyles

0.78

iterranean

0.77

 skepticism

0.73

 eater

0.73

 fats

0.73

 lifestyle

0.72

 enough

0.72

Activations Density 0.023%

terms related to health and well-being, particularly focusing on the concept of 'healthy'

references to health and wellness, particularly focusing on the concept of being healthy

No Comments

No Known Activations