INDEX

Explanations

trademark-related terms

oai_token-act-pair · gpt-3.5-turbo

references to trademarks and trademark-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ECD

-0.79

agan

-0.75

adra

-0.72

apter

-0.70

ATS

-0.66

 Isles

-0.66

CDC

-0.65

TOR

-0.64

ceans

-0.63

è£ħ

-0.63

POSITIVE LOGITS

 trademark

0.97

 trademarks

0.96

emark

0.95

 infringement

0.94

itionally

0.80

 counterfe

0.79

 registrations

0.78

eers

0.78

ingen

0.76

eer

0.74

Activations Density 0.019%

trademark-related terms

references to trademarks and trademark-related concepts

No Comments

No Known Activations