INDEX

Explanations

religious or philosophical statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to equality and rights

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

enegger

-0.69

 Reported

-0.67

 referen

-0.65

 fielded

-0.63

MAP

-0.62

ONSORED

-0.60

CV

-0.60

anwhile

-0.59

 dubbed

-0.59

 anecd

-0.58

POSITIVE LOGITS

 righteousness

1.04

 glory

0.99

 unto

0.87

 mighty

0.82

 thee

0.82

ye

0.81

 everlasting

0.81

 righteous

0.81

 greatness

0.80

 souls

0.80

Activations Density 1.121%

religious or philosophical statements

phrases related to equality and rights

No Comments

No Known Activations