INDEX

Explanations

phrases related to deception and lies

oai_token-act-pair · gpt-3.5-turbo

phrases related to deception and criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ggles

-0.68

cour

-0.58

cellaneous

-0.58

 Adds

-0.55

 partName

-0.55

algia

-0.55

allas

-0.54

often

-0.54

Adds

-0.52

ofi

-0.52

POSITIVE LOGITS

 beforehand

0.76

 wrong

0.73

 Voldemort

0.73

 Bulgar

0.70

 Malfoy

0.67

 sooner

0.65

 unlawfully

0.64

oldemort

0.63

 anyway

0.62

 illegally

0.62

Activations Density 1.847%

phrases related to deception and lies

phrases related to deception and criminal activities

No Comments

No Known Activations