INDEX

Explanations

specific character sequences

oai_token-act-pair · gpt-3.5-turbo

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

 engagements

-0.71

 aging

-0.71

 ideal

-0.70

 ageing

-0.70

 unprepared

-0.67

 citiz

-0.67

bi

-0.66

 assassin

-0.65

 inactive

-0.65

 sacrificing

-0.65

POSITIVE LOGITS

ÂłÂłÂłÂłÂłÂłÂłÂł

1.09

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.05

PHOTOS

1.01

Bus

0.99

ÂłÂłÂłÂł

0.99

ÂłÂłÂł

0.99

However

0.93

Article

0.91

RESULTS

0.91

Shape

0.90

Activations Density 0.495%

specific character sequences

No Comments

No Known Activations