INDEX

Explanations

phrases related to specific actions or intentions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate targeted actions or objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

NESS

-0.72

wine

-0.71

Optional

-0.71

ms

-0.69

anon

-0.67

TM

-0.66

 Printed

-0.64

soever

-0.64

zek

-0.64

ls

-0.63

POSITIVE LOGITS

 improving

1.35

 preventing

1.32

 preserving

1.26

 bolst

1.25

 boosting

1.23

 ensuring

1.22

 maximizing

1.22

 reducing

1.22

 eliminating

1.21

 enhancing

1.19

Activations Density 0.099%

phrases related to specific actions or intentions

phrases that indicate targeted actions or objectives

No Comments

No Known Activations