INDEX

Explanations

phrases related to legal terms and restrictions

oai_token-act-pair · gpt-3.5-turbo

generic terms and phrases related to permissions and limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rea

-0.77

rex

-0.75

ÃŁ

-0.73

rez

-0.72

plex

-0.67

staking

-0.66

seless

-0.65

ros

-0.64

eps

-0.63

expensive

-0.63

POSITIVE LOGITS

THING

1.20

WHERE

1.07

 conceivable

1.01

 particular

0.95

 other

0.93

body

0.93

ONE

0.91

 sort

0.83

where

0.82

 kind

0.80

Activations Density 0.082%

phrases related to legal terms and restrictions

generic terms and phrases related to permissions and limitations

No Comments

No Known Activations