INDEX

Explanations

references to specific locations or sources

oai_token-act-pair · gpt-3.5-turbo

references to figures or visual representations

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

biased

-0.78

bably

-0.77

âĹ¼

-0.76

onz

-0.75

cffffcc

-0.74

operated

-0.73

icum

-0.71

ersive

-0.70

opped

-0.70

affle

-0.69

POSITIVE LOGITS

 below

1.19

 sidebar

0.97

 above

0.95

 supra

0.91

 Appendix

0.88

 footnote

0.87

www

0.82

FAQ

0.81

 Below

0.79

 http

0.78

Activations Density 0.033%

references to specific locations or sources

references to figures or visual representations

No Comments

No Known Activations