INDEX

Explanations

terms related to companionship or relationships with others

oai_token-act-pair · gpt-3.5-turbo

references to companions or companionship

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hene

-0.67

 Mills

-0.66

ulz

-0.66

 Alexis

-0.65

 Blocks

-0.64

zig

-0.62

 hashes

-0.62

Blocks

-0.62

elt

-0.61

anks

-0.61

POSITIVE LOGITS

 companion

3.95

 companions

2.78

 Companion

2.47

Compan

2.17

 Compan

1.72

compan

1.60

 comrade

1.29

 partner

1.24

 colleague

1.21

 buddy

1.20

Activations Density 0.013%

terms related to companionship or relationships with others

references to companions or companionship

No Comments

No Known Activations