INDEX

Explanations

phrases related to the inherent characteristics or qualities of something

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

ogun

-0.74

nuts

-0.71

EMS

-0.69

ICE

-0.69

oned

-0.66

rom

-0.66

UGE

-0.66

enger

-0.66

arya

-0.65

inka

-0.65

POSITIVE LOGITS

quo

0.85

of

0.83

 incarn

0.74

tenance

0.65

 insofar

0.64

itions

0.64

 nature

0.63

fulness

0.62

 inherent

0.60

OF

0.60

Activations Density 0.029%

phrases related to the inherent characteristics or qualities of something

No Comments

No Known Activations