INDEX

Explanations

words related to specific entities such as names of people, places, or organizations

oai_token-act-pair · gpt-3.5-turbo

names of people or organizations associated with leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥ¼ãĥĨ

-0.62

 referen

-0.57

ãĥ¼ãĥĨãĤ£

-0.55

[|

-0.52

ãĥĩãĤ£

-0.51

$$$$

-0.49

ä»£

-0.48

 thous

-0.47

éĽ

-0.46

lished

-0.46

POSITIVE LOGITS

mel

0.51

NetMessage

0.51

amba

0.49

grim

0.49

gall

0.48

ANS

0.46

han

0.46

olin

0.45

 âĢº

0.45

agy

0.45

Activations Density 2.327%

words related to specific entities such as names of people, places, or organizations

names of people or organizations associated with leadership roles

No Comments

No Known Activations