INDEX

Explanations

years from different centuries

oai_token-act-pair · gpt-3.5-turbo

references to specific decades and centuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.76

MAP

-0.68

 Probe

-0.65

 Piper

-0.65

 Proposition

-0.63

 BALL

-0.63

 Guilty

-0.60

 Opening

-0.59

 unofficial

-0.59

 unethical

-0.59

POSITIVE LOGITS

 respectively

1.00

 alike

0.94

 thirds

0.79

 thereof

0.79

 thereafter

0.77

 versa

0.74

isd

0.72

quarters

0.71

resses

0.70

ilda

0.70

Activations Density 0.167%

years from different centuries

references to specific decades and centuries

No Comments

No Known Activations