INDEX

Explanations

terms related to modifications or adjustments

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to modifications or modding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ģĸ

-0.72

ï¸

-0.71

 Beir

-0.69

¨

-0.65

terday

-0.64

 Lauder

-0.63

 Haram

-0.62

lihood

-0.62

AW

-0.60

 Quarterly

-0.60

POSITIVE LOGITS

ifiable

1.26

ding

1.25

icum

1.24

elled

1.22

ifiers

1.21

ded

1.19

ulo

1.18

ifies

1.18

ifications

1.16

ulators

1.11

Activations Density 0.025%

terms related to modifications or adjustments

words and phrases related to modifications or modding

No Comments

No Known Activations