INDEX

Explanations

numeric figures or product specifications in millimeters

oai_token-act-pair · gpt-3.5-turbo

numerical specifications and measurements related to products

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

 prov

-0.74

atem

-0.67

hammad

-0.66

selves

-0.65

achu

-0.62

ItemTracker

-0.62

 precip

-0.61

 mistaken

-0.61

alysed

-0.59

 Pione

-0.59

POSITIVE LOGITS

%-

1.05

 ILCS

0.89

kHz

0.86

ÃĹ

0.86

Â°

0.84

px

0.83

dfx

0.83

mm

0.79

th

0.79

essor

0.77

Activations Density 0.195%

numeric figures or product specifications in millimeters

numerical specifications and measurements related to products

No Comments

No Known Activations