INDEX

Explanations

words related to body parts and their condition, focusing on eyes and mouth in particular

oai_token-act-pair · gpt-3.5-turbo

anatomical features and body parts related to health and surgery

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

CAST

-0.79

igslist

-0.71

advertising

-0.67

Crime

-0.66

DEM

-0.66

Sund

-0.65

 Flavoring

-0.65

ombie

-0.65

 guiActiveUn

-0.64

ionage

-0.63

POSITIVE LOGITS

 cavity

1.00

 circumference

0.99

 lobe

0.85

 canal

0.82

 hump

0.82

 anatomy

0.82

 diameter

0.81

pan

0.80

stem

0.78

 curv

0.78

Activations Density 0.118%

words related to body parts and their condition, focusing on eyes and mouth in particular

anatomical features and body parts related to health and surgery

No Comments

No Known Activations