INDEX

Explanations

phone numbers

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

ĸļ

-0.71

 twins

-0.62

 prey

-0.59

itched

-0.58

cause

-0.58

 neglected

-0.58

 domest

-0.58

 doomed

-0.57

 opio

-0.57

 Cros

-0.57

POSITIVE LOGITS

 CrossRef

0.69

-+-+

0.68

Fax

0.65

eton

0.64

xxxxxxxx

0.64

prises

0.63

aban

0.63

fax

0.62

aba

0.61

ounty

0.61

Activations Density 0.067%

phone numbers

contact information such as phone numbers and email addresses

No Comments

No Known Activations