INDEX

Explanations

words or phrases related to specific entities

oai_token-act-pair · gpt-3.5-turbo

references to the letter "B"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Gutenberg

-0.70

 dere

-0.63

 Pharaoh

-0.58

rpm

-0.58

 punt

-0.58

 Lerner

-0.57

 acne

-0.57

 Ebola

-0.56

wcsstore

-0.55

 Dire

-0.55

POSITIVE LOGITS

odies

1.24

asket

1.23

amboo

1.22

antam

1.16

isexual

1.15

razen

1.14

izarre

1.14

ibli

1.14

azaar

1.12

OTH

1.12

Activations Density 0.047%

words or phrases related to specific entities

references to the letter "B"

No Comments

No Known Activations