INDEX

Explanations

information about the efficiency or characteristics of vehicles

oai_token-act-pair · gpt-3.5-turbo

concepts related to energy and efficiency metrics

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

izoph

-0.84

aws

-0.74

andals

-0.70

aroo

-0.68

adra

-0.68

zek

-0.64

ande

-0.63

ambo

-0.62

Jere

-0.61

nik

-0.61

POSITIVE LOGITS

 percentage

1.45

 multiplied

1.41

 squared

1.38

 ratio

1.31

 normalized

1.26

 total

1.21

 percentile

1.18

 coefficient

1.17

 fraction

1.17

sum

1.17

Activations Density 0.292%

information about the efficiency or characteristics of vehicles

concepts related to energy and efficiency metrics

No Comments

No Known Activations