INDEX

Explanations

ages and age-related information

oai_token-act-pair · gpt-3.5-turbo

phrases referring to age and service duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

uckland

-0.68

 sqor

-0.64

ventus

-0.63

acons

-0.63

MpServer

-0.63

 morning

-0.63

 empath

-0.62

lves

-0.61

aturday

-0.60

 moments

-0.60

POSITIVE LOGITS

 existence

1.06

 eligibility

1.01

 captivity

0.91

age

0.87

 probation

0.87

 residence

0.85

existence

0.83

 residency

0.82

 usefulness

0.81

 tenancy

0.80

Activations Density 0.101%

ages and age-related information

phrases referring to age and service duration

No Comments

No Known Activations