INDEX

Explanations

names of locations or organizations

oai_token-act-pair · gpt-3.5-turbo

descriptive phrases related to time and historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Vaugh

-0.60

chuk

-0.53

emale

-0.52

'."

-0.49

allery

-0.49

 tiss

-0.48

enegger

-0.48

 Nare

-0.47

 referen

-0.47

nesday

-0.46

POSITIVE LOGITS

)]

0.44

taboola

0.41

pires

0.41

natureconservancy

0.40

)?

0.39

 overt

0.39

IRE

0.37

 overtake

0.36

)—

0.36

ÂŃ

0.35

Activations Density 3.838%

names of locations or organizations

descriptive phrases related to time and historical context

No Comments

No Known Activations