INDEX

Explanations

statements or comments

oai_token-act-pair · gpt-3.5-turbo

expressions of self-reflection and inner dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

catentry

-0.53

istani

-0.43

ForgeModLoader

-0.43

 antioxid

-0.41

istan

-0.41

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.39

channelAvailability

-0.38

 srfAttach

-0.37

Zone

-0.37

thumbnails

-0.37

POSITIVE LOGITS

bye

0.49

GGGG

0.46

riel

0.45

ITNESS

0.45

ĻĤ

0.45

rb

0.44

oooooooo

0.44

uca

0.44

apego

0.44

ierre

0.43

Activations Density 5.962%

statements or comments

expressions of self-reflection and inner dialogue

No Comments

No Known Activations