INDEX

Explanations

phrases related to enjoyment and relaxation

oai_token-act-pair · gpt-3.5-turbo

phrases related to enjoyment and positive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

soDeliveryDate

-1.08

osponsors

-0.70

RFC

-0.69

 organizer

-0.68

vernment

-0.67

 eyebrow

-0.66

 wills

-0.65

 Cree

-0.64

 prone

-0.64

©¶æ

-0.63

POSITIVE LOGITS

 pleasures

1.11

 festivities

0.94

 enjoyment

0.91

 fruits

0.91

 leisure

0.90

 solitude

0.86

 freedoms

0.83

 ride

0.83

 downtime

0.81

 privileges

0.80

Activations Density 0.227%

phrases related to enjoyment and relaxation

phrases related to enjoyment and positive experiences

No Comments

No Known Activations