INDEX

Explanations

references to precision or accuracy

oai_token-act-pair · gpt-3.5-turbo

terms related to margins of error in data or statistics

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

emis

-0.76

arus

-0.75

abad

-0.73

uni

-0.69

tics

-0.68

ibur

-0.67

 dormant

-0.63

din

-0.63

oxide

-0.62

tra

-0.62

POSITIVE LOGITS

 margin

1.23

 margins

1.07

margin

0.87

 favoring

0.80

 SHARES

0.79

 separating

0.79

irth

0.72

 landslide

0.71

 Advantage

0.70

Marg

0.70

Activations Density 0.018%

references to precision or accuracy

terms related to margins of error in data or statistics

No Comments

No Known Activations