INDEX

Explanations

terms related to cancelling out or balancing other factors or values

oai_token-act-pair · gpt-3.5-turbo

terms related to financial adjustments or compensations

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

CRIP

-0.74

Interstitial

-0.72

uay

-0.70

wordpress

-0.65

uj

-0.65

ostic

-0.64

IVERS

-0.63

NetMessage

-0.63

soever

-0.63

 antioxid

-0.63

POSITIVE LOGITS

ting

1.26

ments

0.94

mented

0.91

ment

0.88

ted

0.87

balance

0.82

aneous

0.77

cro

0.73

balanced

0.73

ansas

0.69

Activations Density 0.036%

terms related to cancelling out or balancing other factors or values

terms related to financial adjustments or compensations

No Comments

No Known Activations