INDEX

Explanations

words containing the sequence "yr" and number variations of it

oai_token-act-pair · gpt-3.5-turbo

references to years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Loving

-0.69

 commands

-0.63

 luggage

-0.63

 shove

-0.62

 popcorn

-0.60

 health

-0.60

EMP

-0.59

Blu

-0.59

 porn

-0.58

 fart

-0.58

POSITIVE LOGITS

yr

4.64

yrs

3.26

YR

2.03

yd

1.53

yrus

1.50

yr

1.36

yl

1.35

yn

1.29

yt

1.29

yre

1.27

Activations Density 0.010%

words containing the sequence "yr" and number variations of it

references to years

No Comments

No Known Activations