INDEX

Explanations

words related to painting

oai_token-act-pair · gpt-3.5-turbo

references to types of paint and artistic techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 obedient

-0.78

Mos

-0.66

ONSORED

-0.65

 readiness

-0.63

 GOODMAN

-0.62

responsible

-0.61

 rehearsal

-0.60

 slut

-0.59

 reinforced

-0.59

euro

-0.58

POSITIVE LOGITS

 Paint

2.55

 Draw

1.10

acular

0.92

 reign

0.83

bid

0.83

SourceFile

0.81

 Pavilion

0.76

Bid

0.76

 Pyth

0.73

 Golf

0.71

Activations Density 0.007%

words related to painting

references to types of paint and artistic techniques

No Comments

No Known Activations