INDEX

Explanations

specific mentions of job titles, especially medical ones

oai_token-act-pair · gpt-3.5-turbo

terms related to specialized medical professionals and their areas of expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Pathfinder

-0.72

 Rodgers

-0.70

 Oops

-0.70

 ponies

-0.64

 Pony

-0.64

 Shapiro

-0.64

 Pike

-0.64

 optionally

-0.63

err

-0.63

 arrangements

-0.62

POSITIVE LOGITS

cial

4.41

cia

1.26

cific

1.18

IU

1.15

ealous

1.01

istries

0.99

iatric

0.91

culosis

0.89

iuses

0.87

CIA

0.84

Activations Density 0.027%

specific mentions of job titles, especially medical ones

terms related to specialized medical professionals and their areas of expertise

No Comments

No Known Activations