INDEX

Explanations

technical and numerical information

oai_token-act-pair · gpt-3.5-turbo

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

 eleph

-0.99

Þ

-0.94

 pione

-0.88

 exting

-0.86

aditional

-0.81

ò

-0.79

ß

-0.79

ñ

-0.79

 enthusi

-0.78

anwhile

-0.77

POSITIVE LOGITS

inx

0.54

't

0.50

igg

0.49

ette

0.48

athan

0.48

itely

0.46

--+

0.46

vals

0.46

ename

0.45

val

0.45

Activations Density 0.662%

technical and numerical information

No Comments

No Known Activations