INDEX

Explanations

references to specific clothing items or attire

oai_token-act-pair · gpt-3.5-turbo

references to "outfits" or clothing in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

birth

-0.74

 Quincy

-0.68

interrupted

-0.65

elaide

-0.63

ollo

-0.61

Events

-0.61

 depress

-0.59

vous

-0.59

ollow

-0.58

 grand

-0.58

POSITIVE LOGITS

 apparel

0.99

 outfits

0.92

swick

0.92

 outfit

0.90

ters

0.90

ments

0.87

 worn

0.87

 garments

0.82

glers

0.80

 wearer

0.78

Activations Density 0.009%

references to specific clothing items or attire

references to "outfits" or clothing in various contexts

No Comments

No Known Activations