INDEX

Explanations

specific terms related to a location in Myanmar called Rakhine State

oai_token-act-pair · gpt-3.5-turbo

references to the Rohingya people and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĤ¼ãĤ¦ãĤ¹

-0.65

Spread

-0.63

 conveniently

-0.63

 loophole

-0.56

natureconservancy

-0.55

âĶ

-0.55

\<

-0.55

anwhile

-0.55

swick

-0.55

oglu

-0.55

POSITIVE LOGITS

kefeller

0.89

backer

0.83

restling

0.78

issance

0.74

zl

0.74

heed

0.73

¿

0.72

undo

0.71

ophone

0.71

ighters

0.70

Activations Density 0.095%

specific terms related to a location in Myanmar called Rakhine State

references to the Rohingya people and related terms

No Comments

No Known Activations