INDEX

Explanations

words related to reshaping or reorganizing entities or situations

oai_token-act-pair · gpt-3.5-turbo

references to the concept of reshaping or reorganizing different aspects or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Labrador

-0.74

BuyableInstoreAndOnline

-0.73

 Guilty

-0.66

Family

-0.66

ortium

-0.65

 Dome

-0.64

 Hudson

-0.63

 Defenders

-0.63

 Barton

-0.63

Band

-0.62

POSITIVE LOGITS

 resh

1.41

utterstock

0.89

amorph

0.87

apesh

0.87

aped

0.86

olia

0.82

atters

0.81

uffle

0.80

oult

0.80

aping

0.79

Activations Density 0.005%

words related to reshaping or reorganizing entities or situations

references to the concept of reshaping or reorganizing different aspects or elements

No Comments

No Known Activations