INDEX

Explanations

sentences that contain the word "would" followed by some action

oai_token-act-pair · gpt-3.5-turbo

conditional expressions or hypothetical scenarios

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

ige

-0.53

oken

-0.52

 yours

-0.50

redients

-0.49

resa

-0.49

ryn

-0.49

 Learn

-0.48

isible

-0.48

allo

-0.48

 Discover

-0.48

POSITIVE LOGITS

 would

2.81

would

2.56

 wouldn

2.26

 Would

2.03

 could

1.84

Would

1.80

'd

1.76

 might

1.66

could

1.65

 Wouldn

1.62

Activations Density 0.159%

sentences that contain the word "would" followed by some action

conditional expressions or hypothetical scenarios

No Comments

No Known Activations