INDEX

Explanations

references to organizations, companies, and events in the news

oai_token-act-pair · gpt-3.5-turbo

references to media companies and brands

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

 Emin

-0.66

 pend

-0.65

 predicate

-0.63

å£

-0.60

 elim

-0.59

ishers

-0.58

sed

-0.58

Bloom

-0.58

actionDate

-0.57

sonian

-0.57

POSITIVE LOGITS

Ltd

1.08

 Manager

0.91

 Holdings

0.84

 Limited

0.83

LLC

0.79

 Foundation

0.78

 Management

0.72

 Holding

0.72

 Executive

0.72

wide

0.72

Activations Density 0.266%

references to organizations, companies, and events in the news

references to media companies and brands

No Comments

No Known Activations