INDEX

Explanations

positive descriptions of physical and mental well-being

oai_token-act-pair · gpt-3.5-turbo

phrases and descriptors related to quality and condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Egyptians

-0.70

arers

-0.66

 Bene

-0.66

ammers

-0.64

 Maxim

-0.62

 Helpful

-0.61

 Chim

-0.61

ãĤ©

-0.61

Dyn

-0.61

Dai

-0.60

POSITIVE LOGITS

 limbo

0.89

erness

0.86

 orbit

0.84

 mode

0.84

 infancy

0.79

 wilderness

0.78

 twilight

0.74

 vein

0.73

shape

0.72

 capacity

0.71

Activations Density 0.576%

positive descriptions of physical and mental well-being

phrases and descriptors related to quality and condition

No Comments

No Known Activations