INDEX

Explanations

sequences related to job offers and rejections

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to contractual obligations and employment situations

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

 Malays

-0.61

nation

-0.59

atl

-0.57

Mos

-0.57

journal

-0.56

League

-0.55

BN

-0.55

license

-0.54

Shar

-0.54

official

-0.54

POSITIVE LOGITS

 whichever

0.80

 prest

0.73

 predetermined

0.71

 elig

0.71

oldown

0.70

ichever

0.68

 increments

0.66

oother

0.64

 magically

0.63

 automatically

0.62

Activations Density 1.649%

sequences related to job offers and rejections

terms and phrases related to contractual obligations and employment situations

No Comments

No Known Activations