INDEX

Explanations

positive emotional words or terms related to relationships

oai_token-act-pair · gpt-3.5-turbo

terms related to love and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 calculations

-0.72

 routines

-0.67

 experiments

-0.66

 traject

-0.66

 scraps

-0.65

 adaptations

-0.63

 seminars

-0.60

 nightly

-0.60

 levers

-0.60

 slots

-0.60

POSITIVE LOGITS

âĢİ

1.01

 signifies

0.84

xual

0.83

É

0.77

/,

0.76

 refers

0.74

 denotes

0.74

notation

0.73

abl

0.71

channelAvailability

0.71

Activations Density 0.257%

positive emotional words or terms related to relationships

terms related to love and relationships

No Comments

No Known Activations