INDEX

Explanations

references to interviews conducted through various communication methods, such as phone calls or emails

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

edia

-0.81

Mods

-0.70

 Regulations

-0.67

 aven

-0.66

 Confederate

-0.66

 inflicting

-0.63

wre

-0.61

 disliked

-0.61

 Directive

-0.60

 corpor

-0.57

POSITIVE LOGITS

 telephone

1.07

 interview

1.05

 phone

1.03

 Skype

0.94

 translator

0.90

 interviewed

0.84

 interviewer

0.83

 emailed

0.79

 interviews

0.78

 TODAY

0.78

Activations Density 0.106%

references to interviews conducted through various communication methods, such as phone calls or emails

No Comments

No Known Activations