INDEX

Explanations

values associated with financial transactions

oai_token-act-pair · gpt-3.5-turbo

monetary amounts in the context of sports transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aval

-0.70

 drives

-0.68

Wem

-0.66

 frequ

-0.63

 Fatal

-0.63

 Niet

-0.60

 commissioner

-0.59

 Mandal

-0.59

 exha

-0.59

 Fired

-0.59

POSITIVE LOGITS

 (Â£

1.27

illion

1.22

-$

1.03

Â£

0.95

ilion

0.95

âĤ¬

0.90

 euros

0.90

/$

0.88

 dollars

0.85

+.

0.84

Activations Density 0.022%

values associated with financial transactions

monetary amounts in the context of sports transactions

No Comments

No Known Activations