INDEX

Explanations

terms related to invitations and suggestions

oai_token-act-pair · gpt-3.5-turbo

words related to invitations

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

bard

-0.73

avia

-0.69

ther

-0.63

 Aerospace

-0.61

 Certification

-0.60

 Rite

-0.58

 Position

-0.58

urgy

-0.58

 Bearing

-0.58

 Difference

-0.58

POSITIVE LOGITS

 invitations

1.15

 guests

1.02

 invitation

0.99

 invite

0.84

unin

0.82

 invites

0.81

 inviting

0.80

naires

0.78

 attendees

0.76

Inv

0.75

Activations Density 0.022%

terms related to invitations and suggestions

words related to invitations

No Comments

No Known Activations