INDEX

Explanations

numbers indicating ordinal positions or rankings, such as "1st," "2nd," "3rd," etc

oai_token-act-pair · gpt-3.5-turbo

ordinal numbers and rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Downloadha

-0.79

 Canaver

-0.72

bos

-0.70

bath

-0.69

etting

-0.67

ptin

-0.67

mbuds

-0.63

obs

-0.63

sav

-0.63

zai

-0.62

POSITIVE LOGITS

 Amendment

1.00

 Circuit

0.92

 percentile

0.89

 Avenue

0.88

 UPDATE

0.86

 Degree

0.86

 Annual

0.85

ousand

0.83

 Place

0.82

 inning

0.81

Activations Density 0.037%

numbers indicating ordinal positions or rankings, such as "1st," "2nd," "3rd," etc

ordinal numbers and rankings

No Comments

No Known Activations