INDEX

Explanations

references to peer-to-peer interactions or systems

oai_token-act-pair · gpt-3.5-turbo

terms related to peer review and peer-to-peer systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

enegger

-0.92

mes

-0.74

obiles

-0.73

ÄŁ

-0.69

ichick

-0.69

 Liberties

-0.69

tti

-0.68

RANT

-0.67

ABE

-0.65

 Kham

-0.65

POSITIVE LOGITS

Reviewed

0.94

reviewed

0.91

 reviewed

0.89

age

0.88

peer

0.84

less

0.83

 peer

0.82

lessly

0.80

wise

0.79

hood

0.78

Activations Density 0.040%

references to peer-to-peer interactions or systems

terms related to peer review and peer-to-peer systems

No Comments

No Known Activations