INDEX

Explanations

contact information, such as phone numbers and email addresses

oai_token-act-pair · gpt-3.5-turbo

contact information such as phone numbers and email addresses

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

 stacking

-0.75

phabet

-0.74

raints

-0.74

idious

-0.72

 accompanying

-0.72

 repatri

-0.68

 palate

-0.65

Äĩ

-0.65

 storyline

-0.64

 scrolling

-0.63

POSITIVE LOGITS

Fax

0.87

INFO

0.77

GH

0.73

0.72

Tel

0.69

 toll

0.68

FREE

0.67

auld

0.67

Email

0.66

Activations Density 0.106%

contact information, such as phone numbers and email addresses

contact information such as phone numbers and email addresses

No Comments

No Known Activations