INDEX

Explanations

terms related to encryption and encoding

oai_token-act-pair · gpt-3.5-turbo

terms related to encryption and encoding

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

 Louie

-0.80

 Towns

-0.76

Hus

-0.74

illary

-0.72

____

-0.70

 Rush

-0.68

 benches

-0.68

ndra

-0.67

 Huss

-0.67

Ao

-0.66

POSITIVE LOGITS

 encrypted

2.61

enc

2.53

 encoding

2.33

 encrypt

2.24

encrypted

2.22

 encoded

2.18

 decrypt

2.18

 encode

1.99

Enc

1.98

 decoding

1.61

Activations Density 0.044%

terms related to encryption and encoding

terms related to encryption and encoding

No Comments

No Known Activations