INDEX

Explanations

words related to positions or viewpoints on various issues or topics

oai_token-act-pair · gpt-3.5-turbo

references to positions or opinions on various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Interstitial

-0.80

NetMessage

-0.75

cing

-0.73

ined

-0.72

esters

-0.69

usted

-0.68

sample

-0.67

 Sparkle

-0.65

nova

-0.63

ining

-0.62

POSITIVE LOGITS

 stance

1.51

 stances

1.30

 reversal

0.88

 posture

0.85

yip

0.84

 position

0.82

 plank

0.82

 positions

0.78

 towards

0.77

olicy

0.76

Activations Density 0.010%

words related to positions or viewpoints on various issues or topics

references to positions or opinions on various issues

No Comments

No Known Activations