INDEX

Explanations

phrases related to who designed or created something

oai_token-act-pair · gpt-3.5-turbo

instances referencing the creator or origin of an object or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Status

-0.81

SPONSORED

-0.79

wp

-0.78

uality

-0.77

Interstitial

-0.75

Role

-0.74

ãĤ¦ãĤ¹

-0.73

thumbnails

-0.73

inventoryQuantity

-0.73

uin

-0.72

POSITIVE LOGITS

 combining

1.05

 virtue

0.99

 professionals

0.91

 volunteers

0.86

 renowned

0.86

 accident

0.84

 someone

0.84

 multiplying

0.82

 famed

0.81

 acclaimed

0.78

Activations Density 0.147%

phrases related to who designed or created something

instances referencing the creator or origin of an object or concept

No Comments

No Known Activations