INDEX

Explanations

references to the term "Access."

oai_token-act-pair · gpt-3.5-turbo

references to "Access," particularly in relation to availability and participation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

fried

-0.70

otto

-0.68

 nucleus

-0.68

 thou

-0.67

pun

-0.67

uo

-0.65

 quart

-0.63

 merry

-0.63

eters

-0.63

 definite

-0.63

POSITIVE LOGITS

 Access

3.86

Access

2.95

access

2.38

 access

2.11

 accessibility

1.69

accessible

1.41

 accessing

1.38

 accessed

1.29

 accessible

1.24

 Authentication

1.20

Activations Density 0.013%

references to the term "Access."

references to "Access," particularly in relation to availability and participation in various contexts

No Comments

No Known Activations