INDEX

Explanations

phrases that involve financial or economic terms

oai_token-act-pair · gpt-3.5-turbo

phrases containing quotes or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

zona

-0.79

PHI

-0.67

HOU

-0.67

anus

-0.65

endor

-0.64

 authorize

-0.64

eca

-0.64

feed

-0.62

rays

-0.62

 ç¥ŀ

-0.62

POSITIVE LOGITS

ccording

1.20

Meanwhile

0.99

Experts

0.97

JUST

0.95

Speaking

0.89

Elsewhere

0.86

SHARE

0.83

Despite

0.82

Prosecutors

0.81

Officials

0.80

Activations Density 0.091%

phrases that involve financial or economic terms

phrases containing quotes or statements

No Comments

No Known Activations