INDEX

Explanations

measurements expressed in physical dimensions

oai_token-act-pair · gpt-3.5-turbo

measurements and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Proc

-0.80

 glitch

-0.75

 postponed

-0.75

íķ

-0.65

 privatization

-0.63

ynchronous

-0.60

 cancelled

-0.60

 doomed

-0.59

lag

-0.59

Phase

-0.59

POSITIVE LOGITS

 inches

1.67

 centimeters

1.57

cm

1.38

 inch

1.36

cm

1.36

 feet

1.36

inches

1.32

âĢ³

1.22

mm

1.20

cms

1.18

Activations Density 0.110%

measurements expressed in physical dimensions

measurements and dimensions

No Comments

No Known Activations