INDEX

Explanations

phrases related to trademarks and intellectual property

oai_token-act-pair · gpt-3.5-turbo

terms related to trademarks and their registration status

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

ECD

-0.87

 Isles

-0.75

adra

-0.74

agan

-0.71

ilon

-0.66

adh

-0.65

itate

-0.64

ersion

-0.64

 Masquerade

-0.63

Pg

-0.63

POSITIVE LOGITS

emark

0.98

 trademark

0.97

 trademarks

0.94

 infringement

0.83

itionally

0.80

ed

0.78

eers

0.78

 counterfe

0.78

efined

0.75

ively

0.73

Activations Density 0.020%

phrases related to trademarks and intellectual property

terms related to trademarks and their registration status

No Comments

No Known Activations