INDEX

Explanations

professionals and their respective roles or titles

oai_token-act-pair · gpt-3.5-turbo

titles and positions of individuals within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 surgeons

-0.64

uder

-0.61

rums

-0.61

 unbeliev

-0.60

eneg

-0.60

apo

-0.58

Doctors

-0.58

IRE

-0.56

lie

-0.56

 stret

-0.55

POSITIVE LOGITS

 emer

1.07

 extraord

0.91

itatively

0.84

director

0.76

uably

0.76

 curator

0.70

 director

0.67

Ny

0.66

NX

0.65

veland

0.64

Activations Density 0.099%

professionals and their respective roles or titles

titles and positions of individuals within organizations

No Comments

No Known Activations