INDEX

Explanations

mention of trademarks or actions related to trademarks

oai_token-act-pair · gpt-3.5-turbo

references to trademarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cells

-0.78

grades

-0.76

qs

-0.73

seq

-0.69

esley

-0.67

als

-0.66

iles

-0.64

 Chap

-0.62

iew

-0.62

alloc

-0.62

POSITIVE LOGITS

 trademark

4.17

 trademarks

2.99

 patented

1.84

 patent

1.71

 Patent

1.45

 patents

1.43

 Trad

1.35

 copyright

1.30

 logo

1.26

 tradem

1.22

Activations Density 0.023%

mention of trademarks or actions related to trademarks

references to trademarks

No Comments

No Known Activations