INDEX

Explanations

references to authors and their works

oai_token-act-pair · gpt-3.5-turbo

references to authors and their works

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

osta

-0.71

bath

-0.69

-|

-0.68

vere

-0.66

dash

-0.64

ooth

-0.64

angs

-0.64

jobs

-0.63

eg

-0.61

ntil

-0.61

POSITIVE LOGITS

 author

3.82

 authors

2.52

 Author

2.38

author

2.24

 AUTHOR

2.10

Author

2.01

 Authors

1.98

 writer

1.97

 novelist

1.82

authors

1.69

Activations Density 0.020%

references to authors and their works

references to authors and their works

No Comments

No Known Activations