INDEX

Explanations

phrases related to simplicity, efficiency, affordability, and utility in products

oai_token-act-pair · gpt-3.5-turbo

terms related to efficiency and cost-effectiveness

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

pta

-0.87

acan

-0.82

 Deaths

-0.80

orsi

-0.77

section

-0.77

cern

-0.72

sections

-0.71

ortmund

-0.71

 Struggle

-0.70

moil

-0.69

POSITIVE LOGITS

 affordable

1.60

 inexpensive

1.58

 efficient

1.54

 scalable

1.49

 accessible

1.45

 convenient

1.44

 economical

1.42

 durable

1.42

 versatile

1.41

 reusable

1.38

Activations Density 0.246%

phrases related to simplicity, efficiency, affordability, and utility in products

terms related to efficiency and cost-effectiveness

No Comments

No Known Activations