INDEX

Explanations

phrases related to emotions and personal experiences

oai_token-act-pair · gpt-3.5-turbo

expressions of opinion or emotional sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

emale

-0.74

 eleph

-0.70

obbies

-0.64

culosis

-0.62

inav

-0.62

ãĤ©

-0.55

rict

-0.54

vertisements

-0.54

 subur

-0.54

elight

-0.54

POSITIVE LOGITS

 apologies

0.57

 Xperia

0.56

_>

0.55

 patience

0.53

 Zelda

0.52

 Flavoring

0.51

 spoiler

0.51

 Pinball

0.50

 OnePlus

0.49

 Conor

0.47

Activations Density 1.907%

phrases related to emotions and personal experiences

expressions of opinion or emotional sentiment

No Comments

No Known Activations