INDEX

Explanations

quotations and direct speech

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 neocons

-0.87

 favoring

-0.82

 favorably

-0.82

 nutshell

-0.80

 egreg

-0.79

 willfully

-0.79

 leverage

-0.77

 aligned

-0.76

 honoring

-0.75

 preempt

-0.74

POSITIVE LOGITS

Parents

0.98

Police

0.98

 apologised

0.95

However

0.94

Girls

0.93

Investigators

0.93

Coun

0.93

Doctors

0.92

Shape

0.91

Researchers

0.90

Activations Density 0.500%

quotations and direct speech

No Comments

No Known Activations