INDEX

Explanations

terms related to advocating or endorsing different causes or products

oai_token-act-pair · gpt-3.5-turbo

expressions related to promotion and advocacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

psons

-0.73

ft

-0.72

plets

-0.67

gging

-0.66

 Reserv

-0.66

 Manor

-0.64

dra

-0.63

vette

-0.63

thing

-0.63

dal

-0.62

POSITIVE LOGITS

 promoting

1.05

 promotes

0.99

 promotion

0.99

 promote

0.92

 dissemin

0.88

ourage

0.83

 Promotion

0.82

 promoted

0.78

 incent

0.74

ãħĭ

0.74

Activations Density 0.018%

terms related to advocating or endorsing different causes or products

expressions related to promotion and advocacy

No Comments

No Known Activations