INDEX

Explanations

instances of the word "fraud" and related terms within documents

oai_token-act-pair · gpt-3.5-turbo

terms related to fraud and fraudulent activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

area

-0.80

Duration

-0.74

 adaptations

-0.67

accompan

-0.67

 inspiration

-0.66

ä

-0.66

 duty

-0.64

çĦ

-0.63

 sunrise

-0.62

 experimental

-0.61

POSITIVE LOGITS

raud

1.43

ulent

1.11

 Fraud

0.80

gage

0.77

ware

0.77

ulence

0.77

piracy

0.77

razil

0.75

vertising

0.75

 skim

0.72

Activations Density 0.032%

instances of the word "fraud" and related terms within documents

terms related to fraud and fraudulent activities

No Comments

No Known Activations