INDEX

Explanations

dates and historical events

oai_token-act-pair · gpt-3.5-turbo

references to significant historical events and their associated dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

PHOTOS

-0.95

VIDEO

-0.95

FOX

-0.85

ratom

-0.83

 cringe

-0.83

 skew

-0.82

 shaming

-0.81

 takedown

-0.80

 slam

-0.80

 playbook

-0.80

POSITIVE LOGITS

 renamed

0.98

 incorpor

0.96

 thence

0.95

 appointed

0.94

 enlarged

0.91

 transferred

0.90

 secondly

0.90

 reorgan

0.90

 Territ

0.89

 merged

0.88

Activations Density 0.580%

dates and historical events

references to significant historical events and their associated dates

No Comments

No Known Activations