INDEX

Explanations

instances of direct or close personal experience or investigation

oai_token-act-pair · gpt-3.5-turbo

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

anty

-0.80

ammy

-0.77

Ki

-0.74

yg

-0.65

otta

-0.64

IRO

-0.62

itialized

-0.60

 DRAG

-0.60

 Roots

-0.56

icent

-0.56

POSITIVE LOGITS

aneously

0.79

 afterwards

0.76

":"","

0.75

 because

0.73

 afterward

0.72

 before

0.72

ãĢĤ

0.68

 during

0.67

 lest

0.67

 beforehand

0.66

Activations Density 0.300%

instances of direct or close personal experience or investigation

No Comments

No Known Activations