INDEX

Explanations

words related to expectations or norms

oai_token-act-pair · gpt-3.5-turbo

phrases related to expectations or societal norms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Blaz

-0.56

Ey

-0.55

Kis

-0.54

 Flavoring

-0.54

redo

-0.53

 Bulgar

-0.51

 stru

-0.51

owitz

-0.51

 Bohem

-0.49

 Quote

-0.49

POSITIVE LOGITS

to

1.06

to

0.95

TO

0.77

toc

0.71

ered

0.69

entious

0.69

Disclaimer

0.67

 "$:/

0.67

ta

0.67

ALLY

0.67

Activations Density 0.026%

words related to expectations or norms

phrases related to expectations or societal norms

No Comments

No Known Activations