INDEX

Explanations

Japanese characters

oai_token-act-pair · gpt-3.5-turbo

specific encoded symbols or characters

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

 Mole

-0.71

Faw

-0.67

 Bates

-0.65

aiman

-0.64

 Seller

-0.62

phant

-0.62

 Estimates

-0.61

 Physicians

-0.60

atus

-0.60

kefeller

-0.60

POSITIVE LOGITS

æĿ

0.98

 either

0.87

him

0.77

à

0.69

edo

0.68

Mot

0.66

either

0.66

 footing

0.66

him

0.65

 oneself

0.62

Activations Density 0.000%

Japanese characters

specific encoded symbols or characters

No Comments

No Known Activations