INDEX

Explanations

details related to facial features and injuries

oai_token-act-pair · gpt-3.5-turbo

references to facial features and characteristics

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

aday

-0.76

uden

-0.74

ensable

-0.73

rote

-0.72

æ©Ł

-0.71

 Pharma

-0.70

 Blackwell

-0.69

MQ

-0.68

geist

-0.68

 Clever

-0.66

POSITIVE LOGITS

 hair

1.03

 expressions

1.01

 recognition

0.93

 facial

0.90

 portraits

0.89

 expression

0.87

 impressions

0.86

 muscles

0.85

 grooming

0.83

 beard

0.82

Activations Density 0.019%

details related to facial features and injuries

references to facial features and characteristics

No Comments

No Known Activations