INDEX

Explanations

mentions of or references to cash transactions

oai_token-act-pair · gpt-3.5-turbo

references to cash 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

£ı

-0.81

 Galile

-0.81

 Dresden

-0.74

 Godd

-0.72

 Stru

-0.71

ROR

-0.70

 Emin

-0.70

ean

-0.69

 Lenn

-0.68

 Nare

-0.67

POSITIVE LOGITS

mere

1.10

 receipts

0.85

holder

0.84

 withdrawals

0.83

 cash

0.81

 laundering

0.80

 strapped

0.79

cash

0.79

 infusion

0.78

 hoard

0.78

Activations Density 0.025%

mentions of or references to cash transactions

references to cash transactions

No Comments

No Known Activations