INDEX

Explanations

words related to support or approval of something

oai_token-act-pair · gpt-3.5-turbo

pro-terms related to advocacy or support for a particular viewpoint or issue

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

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

ãĤ¼ãĤ¦ãĤ¹

-0.81

 noodles

-0.66

 needles

-0.66

 spears

-0.64

 halls

-0.64

 straw

-0.64

 Halls

-0.63

 strawberries

-0.63

 squid

-0.62

 spoon

-0.61

POSITIVE LOGITS

blems

1.56

ceed

1.46

gression

1.34

digy

1.34

gressive

1.32

secut

1.30

spective

1.30

portion

1.28

spect

1.27

posal

1.26

Activations Density 0.022%

words related to support or approval of something

pro-terms related to advocacy or support for a particular viewpoint or issue

No Comments

No Known Activations